This directory is created automatically and some papers may be mislabeled. Only document within the CiteSeer database are listed. The directory is intended to provide entry points for browsing the database and is not intended to be authoritative. Papers may not appear in all relevant categories. For example, papers in a sub-category may not appear in higher level categories.
61 An Application of Recurrent Nets to Phone Probability Estimation - Robinson (1994)(Correct)
This paper presents an application of recurrent networks for phone probability estimation in large vocabulary speech recognition. The need for efficient exploitation of context information is discusse... / in large vocabulary speech recognition. The need for efficient br of which eight are usable for speaker independent phone recognition. Large
38 The SPHINX-II Speech Recognition System: An Overview - Huang, Alleva, Hon, Hwang, Rosenfeld (1992)(Correct)
In order for speech recognizers to deal with increased task perplexity, speaker variation, and environment variation, improved speech recognition is critical. Steady progress has been made along these... / The SPHINX-II Speech Recognition System An Overview br progress in large-vocabulary speaker-independent continuous speech
29 Person identification using multiple cues - Brunelli, Falavigna (1995)(Correct)
This paper presents a person identification system based on acoustic and visual features. The system is organized as a set of nonhomogeneous classifiers whose outputs are integrated after a normalizat... / of automatic speaker and speech recognition systems. The consequence is br For this work a text independent speaker recognition system based on
28 Learning One More Thing - Sebastian Thrun (1995)(Correct)
Most research on machine learning has focused on scenarios
in which a learner faces a single, isolated learning
task. The lifelong learning framework assumes that the
learner encounters a multitude of... / approaches to speech recognition learning to recognize br studied in character recognition speech understanding and various
27 Maximum Likelihood Linear Transformations for HMM-Based Speech.. - Gales (1998)(Correct)
This paper examines the application of linear transformations for speaker and environmental
adaptation in an HMM-based speech recognition system. In particular, transformations
that are trained in a m... / For Hmm-Based Speech Recognition M.j.f. Gales May br adaptation transforms to a speaker-independent modelset they are applied
24 The Use of Context in Large Vocabulary Speech Recognition - Odell (1995)(Correct)
decide which contexts are similar and can share parameters. A key feature of
this approach is that it allows the construction of models which are dependent upon contextual
effects occurring across wo... / Context in Large Vocabulary Speech Recognition Julian James Odell br a variety of large vocabulary speaker independent continuous speech
20 The Saphira Architecture: A Design for Autonomy - Konolige, Myers, Ruspini, Saffiotti (1997)(Correct)
Journal of Experimental and Theoretical Artificial Intelligence (JETAI) 9, 1997, 215-235.
Special issue on Architectures for Physical Agents.
Mobile robots, if they areto perform useful tasks andbecom... / continuous speech recognition system called CORONA br head. Flakey also has a speaker-independent continuous speech
19 Interactive Translation of Conversational Speech - Waibel (1996)(Correct)
iscuss their usability
and performance.
1.0 Introduction
Multilinguality will take on spoken form when information services are to extend beyond
national boundaries or across language groups. Databa... / Multilingual Speech Recognition and Understanding for br recognizers e.g.digits to speaker independent continuous speech large
18 Performance Of The Ibm Large Vocabulary Continuous Speech Recognition .. - Bahl Balakrishnan-Aiyer Bellgarda(Correct)
In this paper we discuss various experimental results using
our continuous speech recognition system on the Wall
Street Jounal task. Experiments with different feature extraction
methods, varying amou... / Large Vocabulary Continuous Speech Recognition System On The Arpa Wall br We will concentrate on the speaker-independent portion of the database.
17 A Portable Multimedia Terminal for Personal Communications - Sheng (1992)(Correct)
this paper, we will focus on several of the major design issues behind the portable multimedia
terminal: spectrally efficient picocellular networking, low-power digital design, video data
compression,... / is a critical issue. By using speech recognition and pen-based input br input supported by a large speaker-independent recognizers placed on the
16 Flexible Speaker Adaptation Using Maximum Likelihood Linear Regression - Leggetter, Woodland (1995)(Correct)
The maximum likelihood linear regression (MLLR) approach
for speaker adaptation of continuous density mixture Gaussian
HMMs is presented and its application to static and incremental
adaptation for bo... / which tune an existing speech recognition system to a new speaker are br progress has been made in speaker independent SI recognition system
16 Unification-based Multimodal Integration - Johnston, Cohen, McGee, Oviatt.. (1997)(Correct)
Recent empirical research has shown conclusive
advantages of multimodal interaction
over speech-only interaction for mapbased
tasks. This paper describes a multimodal
language processing architecture
... / speech and pen utilizing speech recognition and recognition of gestures br is built using a continuous speaker-independent recognizer commercially
16 Speaker Adaptation Using Combined Transformation and Bayesian Methods - Digalakis, Neumeyer (1995)(Correct)
Adapting the parameters of a statistical speaker-independent continuous-speech recognizer
to the speaker and the channel can significantly improve the recognition performance
and robustness of the sys... / INTRODUCTION Automatic speech recognition performance degrades rapidly br parameters of a statistical speaker-independent continuous-speech
15 High Performance Speaker-Independent Phone Recognition Using CDHMM - Lamel, Gauvain (1993)(Correct)
In this paper we report high phone accuracies on three corpora:
WSJ0, BREF and TIMIT. The main characteristics of the phone recognizer
are: high dimensional feature vector (48), context- and genderdep... / interest in portable speech recognition components there is a br High Performance Speaker-Independent Phone Recognition Using
15 Speaking In Shorthand - A Syllable-Centric Perspective For.. - Greenberg (1998)(Correct)
Current-generation automatic speech recognition (ASR) systems model spoken discourse as a linear sequence of words and phones. Because it is unusual for every phone within a word to be pronounced in a... / Variation for Automatic Speech Recognition Kekrade May - br of large-vocabulary speaker-independent speech recognition systems
15 Predicting Unseen Triphones With Senones - Hwang, Huang, Alleva (1993)(Correct)
In large-vocabulary speech recognition, the decoder often encounters triphones that are not covered in the training data. These unseen triphones are usually represented by corresponding diphones or co... / In large-vocabulary speech recognition the decoder often br We used the DARPA -word speaker-independent Wall Street Journal
15 Speaker Adaptation Using Constrained Estimation of Gaussian Mixtures - Digalakis, Rtischev, Neumeyer (1995)(Correct)
A recent trend in automatic speech recognition systems is the use of continuous mixture-density hidden Markov models (HMMs). Despite the good recognition performance that these systems achieve on aver... / A recent trend in automatic speech recognition systems is the use of br data and it approaches the speaker-independent accuracy achieved for
14 Large Vocabulary Continuous Speech Recognition: a Review - Young (1996)(Correct)
This article will discuss the principles and architecture of current LVR systems and identify the key issues affecting their future deployment. To illustrate the various points raised, the Cambridge U... / Large Vocabulary Continuous Speech Recognition a Review Steve Young br for large vocabulary speaker independent speech recognition. It is
14 Robust Continuous Speech Recognition Using Parallel Model Combination - Gales, Young (1996)(Correct)
This paper addresses the problem of automatic speech recognition in the presence of
interfering noise. It focuses on the Parallel Model Combination (PMC) scheme, which
has been shown to be a powerfu... / Robust Continuous Speech Recognition Using Parallel Model br these experiments was the RM speaker independent task with either Lynx
14 Large Vocabulary Continuous Speech Recognition: - Steve Young Cambridge (1995)(Correct)
This article will discuss the principles and architecture of current LVR systems and identify
the key issues affecting their future deployment. To illustrate the various points raised, the Cambridge
U... / Large Vocabulary Continuous Speech Recognition Steve Young Cambridge br for large vocabulary speaker independent speech recognition. It is
13 A Spoken Language System For Information Retrieval - Bennacef, Bonneau-Maynard, Gauvain..(Correct)
Spoken language systems aim to provide a natural interface
between humans and computers by using simple and natural dialogues
to enable the user to access stored information. The LIMSI
spoken language... / For The Atis Task. Speech Recognition The Speech Recognizer Is br generator is described. The speaker independent continuous speech
13 Sample Complexity for Learning Recurrent Perceptron Mappings - DasGupta, Sontag (1996)(Correct)
Recurrent perceptron classifiers generalize the usual perceptron model. They correspond
to linear transformations of input vectors obtained by means of "autoregressive movingaverage
schemes", or infin... / applications including the speech recognition task of speaker-independent br speech recognition task of speaker-independent discrimination between
13 Shared-Distribution Hidden Markov Models for Speech Recognition - Hwang, Huang (1991)(Correct)
Parameter sharing plays an important role in statistical modeling since training data are usually limited. On the one hand, we would like to use models that are as detailed as possible. On the other h... / Hidden Markov Models for Speech Recognition Mei-Yuh Hwang Xuedong br triphone models for speaker-independent continuous speech
12 The Role of Voice Input for Human-Machine Communication - Cohen, Oviatt (1994)(Correct)
Optimism is growing that the near future will witness rapid growth in human-computer interaction using voice. System prototypes have recently been built that demonstrate speaker-independent real-time ... / real-time speech recognition and understanding of br been built that demonstrate speaker-independent real-time speech
12 Multiple Approaches To Robust Speech Recognition - Richard Stern Fu-Hua (1992)(Correct)
robust speech recognition for the ATIS task, discussing the
This paper compares several different approaches to robust effectiveness of our methods of acoustical prepreprocessing
in the context of thi... / Multiple Approaches To Robust Speech Recognition Richard M. Stern br with each other for the speaker-independent formance of speech
11 Multiple-Pronunciation Lexical Modeling In A Speaker Independent.. - Wooters, Stolcke (1994)(Correct)
One of the sources of difficulty in speech recognition and understanding is the variability due to alternate pronunciations of words. To address the issue we have investigated the use of multiple-pron... / the sources of difficulty in speech recognition and understanding is the br Lexical Modeling In A Speaker Independent Speech Understanding
11 Adaptive Bimodal Sensor Fusion For Automatic Speechreading - Meier, Hürst, Duchnowski (1996)(Correct)
We present recent work on improving the performance of automated speech recognizers by using additional visual information (Lip-/Speechreading), achieving error reduction of up to 50%. This paper focu... / an existing state-of-the-art speech recognition system a modular MS-TDNN. br Hermann Hild and Alex Waibel. Speaker-Independent Connected Letter
11 Integrated Image and Speech Analysis for Content-Based Video Indexing - Chang (1996)(Correct)
In this paper we study an important problem in
multimedia database, namely, the automatic extraction
of indexing information from raw data
based on video contents. The goal of our research
project is ... / an important application of speech recognition and it has attracted a br detection is general and game speaker independent. In this subsection we
11 Experiments In Speaker Normalisation And Adaptation For Large.. - Pye, Woodland (1997)(Correct)
This paper examines techniques for speaker normalisation
and adaptation that are applied in training with the aim
of removing some of the variability from the speaker independent
models. Two technique... / For Large Vocabulary Speech Recognition D. Pye P.c. Woodland br of the variability from the speaker independent models. Two techniques are
11 Speaker Clustering And Transformation For Speaker Adaptation In.. - Padmanabhan Bahl Nahamoo (1995)(Correct)
A speaker adaptation strategy is described that is based
on finding a subset of speakers, from the training set,
who are acoustically close to the test speaker, and using
only the data from these spe... / In Large-Vocabulary Speech Recognition Systems M. Padmanabhan br of for large-vocabulary speakerindependent systems. Though this
10 Deleted Interpolation And Density Sharing For Continuous Hidden.. - Huang, Hwang, Jiang, Mahajan (1996)(Correct)
As one of the most powerful smoothing techniques, deleted interpolation has been widely used in both discrete and semi-continuous hidden Markov model (HMM) based speech recognition systems. For contin... / Markov model HMM based speech recognition systems. For continuous br general models such as speaker-independent or context-independent
10 Speaker-Independent Continuous Speech Dictation - Gauvain, Lamel, Adda, Adda-Decker (1994)(Correct)
In this paper we report progress made at LIMSI in speaker-independent
large vocabulary speech dictation using newspaper speech corpora. The recognizer
makes use of continuous density HMM with Gaussian... / INTRODUCTION Our speech recognition work focuses on developing br Speaker-Independent Continuous Speech Dictation
10 Recent Advances In JANUS: A Speech Translation System - Woszczyna, Coccaro, Eisele, Lavie.. (1993)(Correct)
We present recent advances from our efforts in increasing coverage,
robustness, generality and speed of JANUS, CMU's
speech-to-speech translation system. JANUS is a speakerindependent
system which tra... / improves performance in the speech recognition module .improved br system. JANUS is a speakerindependent system which translates
10 The HTK Tied-State Continuous Speech Recogniser - Woodland, Young (1993)(Correct)
HTK is a portable software toolkit for developing systems
using continuous density hidden Markov models
developed by the Cambridge University Speech Group.
This paper describes speech recognition expe... / Group. This paper describes speech recognition experiments using HTK based br were evaluated using the speaker independent Feb' Oct' Feb' and
10 Blind Separation of Convolutive Mixtures and an Application in.. - Ehlers, Schuster (1997)(Correct)
In this paper we propose a two-step-algorithm for
the blind separation of convolutive mixtures. We show that
its application to automatic speech recognition in a noisy
environment yields good results.... / an Application in Automatic Speech Recognition in Noisy Environment F. br system . Creation of speaker-independent initial patterns from
10 Language Learning Based On Non-Native Speech Recognition - Silke Witt, Steve Young (1997)(Correct)
This work presents methods of assessing non-native
speech to aid computer-assisted pronunciation teaching.
These methods are based on automatic speech recognition
(ASR) techniques using Hidden Markov ... / Learning Based On Non-Native Speech Recognition Silke Witt Steve Young br produced by a speaker independent recogniser in forced
10 Lexical Modeling in a Speaker Independent Speech Understanding System - Wooters (1993)(Correct)
Over the past 40 years, significant progress has been made in the fields of speech recognition and speech understanding. Current state-of-the-art speech recognition systems are capable of achieving wo... / been made in the fields of speech recognition and speech understanding. br in the fields of speech recognition and speech understanding. Current
10 Word And Acoustic Confidence Annotation For Large Vocabulary Speech.. - Chase(Correct)
We present improvements in confidence annotation of automatic speech recognizer output for large vocabulary, speakerindependent systems. Several strong additions to the set of predictor variables used... / For Large Vocabulary Speech Recognition Lin Chase The Robotics br output for large vocabulary speakerindependent systems. Several strong
9 Empirically Evaluating an Adaptable Spoken Dialogue System - Litman, Pan (1999)(Correct)
Recent technological advances have made it possible to build real-time, interactive
spoken dialogue systems for a wide variety of applications. However, when users
do not respect the limitations of ... / that combines automatic speech recognition ASR text-to-speech TTS br ASR in our platform is speaker-independent grammar-based and supports
9 Experiments in Spoken Document Retrieval at CMU - Siegler Witbrock (1997)(Correct)
We describe our submission to the TREC-6 Spoken Document Retrieval (SDR) track and the speech recognition and
the information retrieval engines. We present SDR evaluation results and a brief analysis.... / Retrieval SDR track and the speech recognition and the information br is a large vocabulary speaker independent fully continuous hidden
9 Recognizing Reverberant Speech With Rasta-Plp - Kingsbury, Morgan (1997)(Correct)
The performance of the PLP, log-RASTA-PLP, and
J-RASTA-PLP front ends for recognition of highly reverberant
speech is measured and compared with the performance
of humans and the performance of an exp... / to reverberation in automatic speech recognition ASR systems is a problem br features for use in speaker-independent continuous speech
9 Analysis and Synthesis of Intonation using the Tilt Model - Taylor(Correct)
This paper introduces the tilt intonational model and describes how this model can be used to automatically analyse and synthesize intonation. In the model, intonation is represented as a linear seque... / completely in automatic speech recognition ASR systems Granstrom br of read and spontaneous speaker independent conversational speech
9 The Generation And Use Of Regression Class Trees For Mllr Adaptation - Gales (1996)(Correct)
Maximum likelihood linear regression (MLLR) is an adaptation technique suitable for both speaker and environmental model-based adaptation. The models are adapted using a set of linear transformations,... / speaker independent SI speech recognition systems are capable of br Current state-of-the-art speaker independent SI speech recognition
9 Model-Based Techniques For Noise Robust Speech Recognition - Gales (1995)(Correct)
observed in terms of both a distance measure, the average Kullback-Leibler number on a feature vector component level, and the effect on word accuracy. For best performance in noise-corrupted environm... / Techniques For Noise Robust Speech Recognition Mark John Francis Gales
8 Remap: Recursive Estimation And Maximization Of A Posteriori.. - Bourlard, Konig, Morgan (1995)(Correct)
In this paper, we briefly describe REMAP, an approach for the training and estimation of posterior probabilities, and report its application to speech recognition. REMAP is a recursive algorithm that ... / In Connectionist Speech Recognition Herv'e Bourlard Zy br word vocabulary speaker independent continuous speech
8 Unsupervised Speaker-Adaptation For Hybrid Hmm-Mlp Continuous Speech.. - Neto, Martins, Almeida (1995)(Correct)
This paper presents an unsupervised technique for speaker-adaptation in the context of continuous speech recognition with a hybrid HMM-MLP system. By unsupervised adaptation we mean that there is no p... / Hybrid Hmm-Mlp Continuous Speech Recognition System Jo ao P. Neto Ciro br approach to largevocabulary speaker-independent continuous speech
8 Experimental Determination of Precision Requirements for.. - Asanovic, Morgan (1991)(Correct)
The impact of reduced weight and output precision on the back-propagation training
algorithm [Wer74, RHW86] is experimentally determined for a feed-forward multilayer
perceptron. In contrast with pr... / for a continuous speech recognition system. The results br A phoneme-based speaker dependent continuous speech
8 Mean and Variance Adaptation within the MLLR Framework - Gales, Woodland (1996)(Correct)
One of the key issues for adaptation algorithms is to modify a large number of parameters
with only a small amount of adaptation data. Speaker adaptation techniques
try to obtain near speaker depend... / speaker independent SI speech recognition systems are capable of br are often based on initial speaker independent SI recognition systems.
7 Experiments In Information Retrieval From Spoken Documents - Hauptmann Jones (1998)(Correct)
This paper describes the experiments performed as part of the
TREC-97 Spoken Document Retrieval Track. The task was to
pick the correct document from 35 hours of recognized speech
documents, based on ... / of words missing from the speech recognition vocabulary experiments br is a large vocabulary speaker independent fully continuous hidden
7 The Spoken Language Component of the Mask Kiosk - Gauvain, Bennacef, Devillers, Lamel, .. (1997)(Correct)
The aim of the Multimodal-Multimedia Automated Service Kiosk (MASK) project is to
pave the way for more advanced public service applications by user interfaces employing
multimodal, multi-media input ... / chosen task and Continuous Speech Recognition Natural Language br with emphasis on the speaker-independent large vocabulary
7 Multimodal Interfaces - Waibel, Vo, Duchnowski, Manke (1995)(Correct)
In this paper, we present an overview of research in our laboratories on Multimodal
Human Computer Interfaces. The goal for such interfaces is to free human computer interaction
from the limitations a... / cues including Speech recognition with lipreading for more br in automatic speech recognition speech processing human and
7 The Karlsruhe-Verbmobil Speech Recognition Engine - Finke, Geutner, Hild, Kemp, Ries.. (1997)(Correct)
Verbmobil, a German research project, aims at machine
translation of spontaneous speech input. The ultimate
goal is the development of a portable machine translator
that will allow people to negotiate... / The Karlsruhe-Verbmobil Speech Recognition Engine Michael Finke br in WER compared to the speaker independent non VTLN system assuming
7 BREF, a Large Vocabulary Spoken Corpus for French - F.Lamel, Gauvain, Eskenazi(Correct)
This paper presents some of the design considerations of BREF, a large
read-speech corpus for French. BREF was designed to provide continuous
speech data for the development of dictation machines, for... / the evaluation of continuous speech recognition systems both br used for speech recognition and speech synthesis in French
7 Evaluation Of Dialog Strategies For A Tourist Information Retrieval.. - Devillers, Bonneau-Maynard (1998)(Correct)
In this paper, we describe the evaluation of the dialog management and response generation strategies being developed for retrieval of touristic information, selected as a common domain for the ARC AU... / metrics are used to measure speech recognition performance and measures br is composed of a -word speaker-independent continuous speech
7 Language Identification Using Phone-based Acoustic Likelihoods - Lamel, Gauvain (1994)(Correct)
In this paper we apply the technique of phone-based acoustic
likelihoods to the problem of languageidentification. The basic idea
is to process the unknownspeech signal by language-specificphone
model... / as well as multi-language speech recognition. The entire corpus contains br first labeled using a set of speakerindependent context-independentphone
6 Variance Compensation Within The Mllr Framework - Gales, Woodland (1996)(Correct)
Speaker adaptation techniques try to obtain near speaker dependent (SD) performance with only small amounts speaker specific data, and are often based on initial speaker independent (SI) recognition s... / speaker independent SI speech recognition systems are capable of br are often based on initial speaker independent SI recognition systems.
6 Speechacts: A Testbed For Continuous Speech Applications - Martin, Kehler (1994)(Correct)
The SpeechActs system is a testbed for building computer
applications utilizing continuous speech input
and speech synthesis output. It supports a variety
of speech recognition (SR) systems and text-t... / It supports a variety of speech recognition SR systems and br as triphones. All are speaker-independent and use only the triphone
6 Automatic Speaker Clustering - Jin, Kubala, Schwartz (1997)(Correct)
This paper presents a fully automatic speaker clustering algorithm, which consists of three components: building a distance matrix based on Gaussian models of the acoustic segments; performing hierarc... / of large vocabulary speech recognition systems. Today almost all br to move the parameters of the speaker independent system towards the speaker
6 A Trainable Rule-based Algorithm for Word Segmentation - Palmer (1997)(Correct)
This paper presents a trainable rule-based algorithm for performing word segmentation. The algorithm provides a simple, language-independent alternative to large-scale lexical-based segmenters requiri... / segmentation is similar to speech recognition in which a system must be br to and recognize the multiple speaker-dependent correct pronunciations of
6 Intonation and dialogue context as constraints for speech recognition - Taylor, King, Isard, Wright (1998)(Correct)
This paper describes a way of using intonation and dialogue
context to improve the performance of an automatic speech recognition
(ASR) system. Our experiments were run on the DCIEM
Maptask corpus, a ... / context as constraints for speech recognition Paul Taylor Simon King br so the results we report are speaker independent. The language models and
6 Acoustic And Language Modeling Of Human And Nonhuman Noises For.. - Schultz, Rogina (1995)(Correct)
In this paper several improvements of our speech-to-speech translation system JANUS on spontaneous human-to-human dialogs are presented. Common phenomena in spontaneous speech are described, followed ... / Human-To-Human Spontaneous Speech Recognition T.schultz And I.rogina br modular system containing a speaker independent recognizer for utterances
6 The LIMSI ARISE System - Lamel Rosset (1998)(Correct)
The LIMSI ARISE system provides vocal access to rail
travel information for main French intercity connections,
including timetables, simulated fares and reservations, reductions
and services. Our goal... / speech recognizer. due to speech recognition a confidence score is br medium vocabulary real-time speaker-independent continuous speech
6 Survey of Current Speech Technology - Rudnicky, Hauptmann (1994)(Correct)
This article describes two technologies, speech recognition and speech synthesis,
that manipulate speech in terms of its information content. Recognition
is the transformation of human speech into tex... / describes two technologies speech recognition and speech synthesis br two technologies speech recognition and speech synthesis that
6 Connectionist Probability Estimation In The Decipher Speech.. - Renals, Morgan, Cohen, Franco (1992)(Correct)
Previously, we have demonstrated that feed-forward networks
may be used to estimate local output probabilities in
hidden Markov model (HMM) speech recognition systems.
Here these connectionist techniq... / Estimation In The Decipher Speech Recognition System Steve Renals br Being Performed Using The Speaker Independent Darpa Rm Database. Our
6 Recent Improvements To The Abbot Large Vocabulary Csr System - Hochberg Renals (1995)(Correct)
ABBOT is the hybrid connectionist-hidden Markov model (HMM)
large-vocabulary continuous speech recognition (CSR) system developed
at Cambridge University. This system uses a recurrent
network to estim... / large-vocabulary continuous speech recognition CSR system developed at br of speech are highly speaker dependent. To minimize this effect
6 Improving Environmental Robustness In Large Vocabulary Speech.. - Woodland, Gales, Pye (1996)(Correct)
This paper describes techniques to improve the robustness
of the HTK large vocabulary speech recognition system to
non-ideal acoustic environments. The primary methods are
single-pass retraining using... / In Large Vocabulary Speech Recognition P.c. Woodland M.j.f. br INTRODUCTION Most work on speaker independent large vocabulary continuous
6 Speech-Based Retrieval Using Semantic Co-Occurrence Filtering - Kupiec, Kimber, Balasubramanian (1994)(Correct)
In this paper we demonstrate that speech recognition can be
effectively applied to information retrieval (IR) applications.
Our system exploits the fact that the intended words of a spoken
query tend ... / paper we demonstrate that speech recognition can be effectively applied br models were initialized from speaker independent models trained on the TIMIT
6 Automatic Generation Of Synthesis Units For Trainable Text-To-Speech.. - Hon Acero Huang (1998)(Correct)
Whistler Text-to-Speech engine was designed so that we can
automatically construct the model parameters from training data.
This paper will describe in detail the design issues of constructing
the syn... / has been well studied in the speech recognition community A senone br speakers the use of a large speaker-independent database like the DARPA's
6 The NIST Speaker Recognition Evaluations: 1996-2001 - Martin, Przybocki (1998)(Correct)
We discuss the history and purposes of the NIST evaluations
of speaker recognition performance. We cover the sites that
have participated, the performance measures used, and the
formats used to report... / coordinated evaluations of speech recognition Figure in fact shows br evaluations of text independent speaker recognition using
6 Lvcsr-Based Language Identification - Schultz, Rogina, Waibel (1996)(Correct)
Automatic language identification is an important problem in building multilingual speech recognition and understanding systems. Building a language identification module for four languages we studied... / in building multilingual speech recognition and understanding systems. br via Large Vocabulary Speaker Independent Continuous Speech
5 Context-Dependent Hybrid HME/HMM Speech Recognition Using Polyphone.. - Fritsch, Finke, Waibel (1997)(Correct)
This paper presents a context-dependent hybrid connectionist speech recognition system that uses a set of generalized hierarchical mixtures of experts (HME) to estimate context-dependent posterior aco... / Hybrid Hme hmm Speech Recognition Using Polyphone Clustering br evaluated on ESST an english speaker-independent spontaneous speech
5 Towards Unrestricted Lip Reading - Meier, Stiefelhagen, Yang, Waibel (1999)(Correct)
Lip reading provides useful information in speech perception
and language understanding, especially when the auditory
speech is degraded. However, many current automatic
lip reading systems impose som... / an existing state-of-the-art speech recognition system a modular Multiple br and A.Waibel. Multi-speaker speaker-independent architectures for the
5 Combining Methods to Improve Speaker Verification Decision - Genoud, Gravier, Bimbot, Chollet (1996)(Correct)
The aim of this paper is to describe how the combination of speaker verification algorithms
with a priori decision thresholds can improve the overall robustness of a real application.
The evaluation... / identification number PIN Speech recognition is performed on all the br recognized using a HMM based speaker independent speech recognizer Gro
5 Improving Acoustic Models By Watching Television - Witbrock, Hauptmann (1998)(Correct)
Obtaining sufficient labelled training data is a persistent difficulty for speech recognition research. Although well transcribed data is expensive
to produce, there is a constant stream of challengin... / a persistent difficulty for speech recognition research. Although well br which is a large-vocabulary speaker-independent continuous speech
5 Speaker Adaptation by Correlation (ABC) - Chen, DeSouza (1997)(Correct)
This paper describes a new rapid speaker adaptation algorithm
using a small amount of adaptation data. This
algorithm, termed adaptation by correlation (ABC), exploits
the intrinsic correlation among ... / We assume that the basic speech recognition system uses HMM's to model br to use the mean vector of the speaker independent system. That leads to
5 Discriminative Training for Continuous Speech Recognition - Reichl, Ruske (1996)(Correct)
Discriminative training techniques for Hidden-Markov
Models were recently proposed and successfully applied for
automatic speech recognition. In this paper a discussion of
the Minimum Classification E... / Training for Continuous Speech Recognition W. Reichl G. Ruske br methods were utilized in speaker independent phoneme recognition
5 Connected Letter Recognition with a Multi-State Time Delay Neural.. - Hild, Waibel (1993)(Correct)
The Multi-State Time Delay Neural Network (MS-TDNN) integrates
a nonlinear time alignment procedure (DTW) and the highaccuracy
phoneme spotting capabilities of a TDNN into a connectionist
speech recog... / a TDNN into a connectionist speech recognition system with word-level br and test set x for the speaker-independent RM Spell-Mode data.
5 Bayesian Learning of Gaussian Mixture Densities for Hidden Markov.. - Gauvain, Lee (1991)(Correct)
An investigation into the use of Bayesian learning of the parameters
of a multivariate Gaussian mixture density has been
carried out. In a continuous density hidden Markov model
(CDHMM) framework, Ba... / robustness in a CDHMM-based speech recognition system so as to improve br was obtained compared to speaker-independent results. Using Baysesian
5 Rasta-Plp Speech Analysis - Hermansky, Morgan, Bayya, Kohn (1991)(Correct)
Most speech parameter estimation techniques are easily influenced by the frequency response of
the communication channel. We have developed a technique that is more robust to such steady-state
spectra... / independent continuous speech recognition corpus were used as the br Resource Management speaker independent continuous speech
5 Speaker Independent Audio-Visual Database For Bimodal Asr - Potamianos, Cosatto, Graf, Roe (1997)(Correct)
This paper describes the audio-visual database collected at AT&T Labs--Research for the study of bimodal speech recognition. To date, this database consists of two multiple speaker parts, namely isola... / for the study of bimodal speech recognition. To date this database br Speaker Independent Audio-Visual Database For
5 Mode preference in a simple data-retrieval task - Rudnicky (1993)(Correct)
This paper describes some recent experiments that
assess user behavior in a multi-modal environment
in which actions can be performed with equivalent
effect in speech, keyboard or scroller modes. Resu... / new technologies such as speech recognition. For activities in a br Sphinx and is capable of speaker-independent continuous speech
5 Signal Processing For Robust Speech Recognition - Stern, Acero, Liu, Ohshima (1996)(Correct)
This chapter compares several di#erent approaches to robust automatic speech recognition.
We review ongoing research in the use of acoustical pre-processing to achieve
robust speech recognition, discu... / Signal Processing For Robust Speech Recognition Richard M. Stern br that are designed to be speaker independent can perform very poorly
5 Lexical Modeling Of Non-Native Speech For Automatic Speech Recognition - Livescu, Glass (2000)(Correct)
This paper examines the recognition of non-native speech in
jupiter, a speaker-independent, spontaneous-speech conversational
system. Because the non-native speech in this
domain is limited and varied... / Speech For Automatic Speech Recognition Karen Livescu And James br speech in jupiter a speaker-independent spontaneous-speech
5 Identifying Non-Linguistic Speech Features - Lamel, Gauvain(Correct)
Over the last decade technological advances have been made
which enable us to envision real-world applications of speech
technologies. It is possible to foresee applications, for example,
information ... / signal. INTRODUCTION As speech recognition technology advances so do br is the development of speaker-independent taskindependent large
5 Audio-Visual Integration In Multimodal Communication - Chen, Rao (1998)(Correct)
In this paper, we review recent research that examines audio-visual integration in multimodal communication. The topics include bimodality in human speech, human and automated lip-reading, facial an... / Image Video Audio Speech Recognition Text-to-Speech Sign br speaker dependent and speaker independent systems and examining
4 CSDC - The MoTiV Car Speech Data Collection - Langmann, Pfitzinger, Schneider.. (1998)(Correct)
A commmon initiative was created between the industrial
partners Philips, Siemens, Bosch, and Volkswagen in the subproject
Man-Machine Interaction of the German governmentfunded
project "MoTiV" (mobil... / on speaker-independent speech recognition in the car. INTRODUCTION br of real circumstances on speaker-independent speech recognition in the
4 Real-Time Lip-Tracking For Lipreading - Stiefelhagen, Meier, Yang(Correct)
This paper presents a new approach to lip tracking for
lipreading. Instead of only tracking features on lips, we
propose to track lips along with other facial features such
as pupils and nostril. In t... / data for the audio-visual speech recognition system. The system has been br the camera. The system is for speaker dependent continuous spelling of
4 Modular Neural Networks for Speech Recognition - Fritsch (1996)(Correct)
In recent years, researchers have established the viability of so called hybrid NN/HMM
large vocabulary, speaker independent continuous speech recognition systems, where neural
networks (NN) are used ... / Modular Neural Networks for Speech Recognition Diploma thesis Jurgen br NN HMM large vocabulary speaker independent continuous speech
4 Towards improving ASR robustness for PSN and GSM telephone.. - Mokbel, Mauuary, Karray, Jouvet.. (1997)(Correct)
In real-life applications, errors in the speech recognition system are mainly due to inefficient detection of speech
Z. segments, unreliable rejection of Out-Of-Vocabulary OOV words, and insufficient... / applications errors in the speech recognition system are mainly due to br in order to perform robust recognition and speech detection for
4 Foreign Accent Classification Using Source Generator Based Prosodic.. - Hansen, Arslan (1995)(Correct)
Speaker accent is an important issue in the formulation of
robust speaker independent recognition systems. Knowledge
gained from a reliable accent classification approach could improve
overall recogni... / also a challenging problem in speech recognition. It is one of the most br in the formulation of robust speaker independent recognition systems.
4 Can Continuous Speech Recognizers Handle Isolated Speech? - Alleva, Huang, Hwang, Jiang (1997)(Correct)
Continuous speech is far more natural and efficient than isolated speech for communication. However, for current state-of-the-art automatic speech recognition systems, isolated speech recognition (ISR... / Keywords Isolated Speech Recognition ISR Continuous Speech br improve the robustness of our speaker-independent CSR system against
4 Video Mail Retrieval Using Voice: Report on Keyword Definition and.. - Jones, Foote, Jones, Young (1994)(Correct)
The report describes the rationale, design, collection and basic statistics of the initial training and test database for the Cambridge Video Mail Retrieval (VMR) Project. This database is intended to... / training data for the speech recognition element and a set of br This should enable better speaker independent acoustic filler models to
4 Identification of Non-Linguistic Speech Features - Gauvain, Lamel (1993)(Correct)
Over the last decade technological advances have been made which enable
us to envision real-world applications of speech technologies. It is
possible to foresee applications where the spoken query is ... / INTRODUCTION As speech recognition technology advances so do br is the development of speaker-independent taskindependent large
4 The Limsi Arise System For Train Travel Information - Lamel Rosset Gauvain (1999)(Correct)
In the context of the LE-3 ARISE project we have been developing a dialog
system for vocal access to rail travel information. The system provides
schedule information for the main French intercity con... / Firstly recording and speech recognition must be active at all times br system. The real-time speaker independent continuous speech
4 Prosodic Cues to Recognition Errors - Hirschberg, Litman, Swerts (1999)(Correct)
We identify methods of distinguishing between correctly
and incorrectly recognized utterances (scored by hand for
semantic concept accuracy) for a speech recognition system,
using acoustic/prosodic ch... / concept accuracy for a speech recognition system using br The speech recognizer is a speaker-independent hidden Markov model system
4 Frame-Discriminative And Confidence-Driven Adaptation For LVCSR - Wallhoff, Willett, Rigoll (2000)(Correct)
Maximum Likelihood Linear Regression (MLLR) has become
the most popular approach for adapting speakerindependent
Hidden Markov Models to a speci c speaker's
characteristics. However, it is well known,... / Large Vocabulary Continuous Speech Recognition LVCSR In supervised br popular approach for adapting speakerindependent Hidden Markov Models to a
4 Interactive Speech Translation in the DIPLOMAT Project - Frederking, Rudnicky, Hogan (1997)(Correct)
The DIPLOMAT rapid-deployment speech translation system is intended to allow naive users to communicate across a language barrier, without strong domain restrictions, despite the errorprone nature of ... / continuous speech recognition system Huang et al. br The Sphinx Ii Hmm-Based Speaker-Independent Continuous Speech
4 The LIMSI SDR System for TREC-8 - Gauvain, de Kercadio, Lamel, Adda(Correct)
In this paper we report on our TREC-8 SDR system, which
combines an adapted version of the LIMSI 1998 Hub-4E transcription
system for speech recognition with an IR system based on the
Okapi term weigh... / transcription system for speech recognition with an IR system based on br to avoid cutting words. . Speaker-independent GMMs corresponding to
4 The LIMSI SDR System for TREC-9 - Gauvain, Lamel, Barras, Adda, de..(Correct)
In this paper we describe the LIMSI Spoken Document Retrieval
system used in the TREC-9 evaluation. This system combines
an adapted version of the LIMSI 1999 Hub-4E transcription
system for speech rec... / transcription system for speech recognition with text-based IR methods. br measure with each word. The speaker-independent large vocabulary
4 Speaker Dependent Keyword Spotting for Accessing Stored Speech - Knill, Young (1994)(Correct)
This report investigates the use of a speaker-dependent HMM word-spotter to retrieve spoken messages. The baseline word-spotter consists of a parallel network of keyword and background filler models. ... / Keywords word-spotting speech recognition information retrieval. br word-spotting performance of speaker-independent models with and without
4 MeetingManager: A Collaborative Tool in the Intelligent Room - Oh, Tuchinda, Wu (2001)(Correct)
this paper,
we describe our MeetingManager system, a multiuser
multimodal collaboration tool for planning, facilitating,
and browsing structured meetings unknown MeetingManager: A Collaborative Tool i... / speaker-independent speech recognition eye-gaze tracking and br such as large-vocabulary speaker-independent speech recognition
3 Combining Local PCA and Radial Basis Function Networks for Speaker.. - Furlanello, Giuliani (1995)(Correct)
Complex multidimensional data may naturally require the decomposition of a regression/classification problem over local regions. Moreover, both global and local anisotropy can be present. We propose t... / a major problem arising when speech recognition technology is moved from br speech material for speaker independent utterances from
3 Field Trials of a Telephone Service for Rail Travel Information - Lamel Gauvain(Correct)
This paper reports on the RAILTEL field trial carried
out by LIMSI, to assess the technical adequacy of available speech
technology for interactive vocal access to static train timetable information.
... / and played to the user. A. Speech Recognition The speech recognizer is br spokenquery is decodedby a speaker independent continuous speech
3 Using Prosodic Information to Constrain Language Models for Spoken.. - Paul Taylor (1996)(Correct)
We present work intended to improve speech recognition performance
for computer dialogue by taking into account the
way that dialogue context and intonational tune interact to
limit the possibilities ... / work intended to improve speech recognition performance for computer br and testing. In an a speaker independent open test the first choice
3 Preprocessing Of Visual Speech Under Real World Conditions - Meier, Stiefelhagen, Yang (1997)(Correct)
In this paper we present recent work on integration of visual information (automatic lip-reading) with acoustic speech for better overall speech recognition. We have developed a modular system for fle... / speech for better overall speech recognition. We have developed a br mode first multi speaker speaker independent tests show promising
3 Adaptively Growing Hierarchical Mixtures of Experts - Fritsch, Finke, Waibel(Correct)
We propose a novel approach to automatically growing and pruning
Hierarchical Mixtures of Experts. The constructive algorithm proposed
here enables large hierarchies consisting of several hundred
expe... / version of the JANUS speech recognition system using a subset of br Switchboard large-vocabulary speaker-independent continuous speech
3 An Hmm-Based Cepstral-Domain Speech Enhancement System - Seymour, Niranjan (1994)(Correct)
This paper describes a method of enhancing speech
corrupted by additive uncorrelated noise. The approach
adopted is to use cepstral-domain hidden
Markov models to determine statistics of the clean
spe... / as a front end to a computer speech recognition system. When an enhanced br and vocabulary-independent speaker-independent speech models are
3 Training Data Clustering For Improved Speech Recognition - Sankar, Beaufays, Digalakis (1995)(Correct)
We present an approach to cluster the training data
for automatic speech recognition (ASR). A relativeentropy
based distance metric between training data
clusters is defined. This metric is used to hi... / Data Clustering For Improved Speech Recognition Ananth Sankar Francoise br noise. Even in traditional speaker-independent recognition systems that
3 Improving Performance On Switchboard By Combining Hybrid HME/HMM And.. - Fritsch, Finke (1997)(Correct)
This paper presents results of our efforts on combining
standard mixture of Gaussians acoustic modeling
[10] with a context-dependent hybrid connectionist
HME/HMM architecture [3, 4] for the Switchboa... / fields being tackled by the speech recognition community. Sites achieved br derivatives. We normalize for speaker dependent vocal tract lengths by
3 Multimodal Human-Computer Interaction - Vo, Waibel (1993)(Correct)
While human-to-human communication takes advantage of an
abundance of information and cues, human-computer interaction
is limited to only a few input modalities (usually only
keyboard and mouse) and p... / multimodal interface speech recognition lip-reading eye-tracking br as a large vocabulary speaker independent speech recognition server
3 Use Of Gaussian Selection In Large Vocabulary Continuous Speech.. - Knill, Gales, Young (1996)(Correct)
This paper investigates the use of Gaussian Selection (GS) to reduce the state likelihood computation in HMM-based systems. These likelihood calculations contribute significantly (30 to 70%) to the co... / Large Vocabulary Continuous Speech Recognition Using Hmms K.m.knill br recognition accuracy on a k speaker-independent task to be maintained up to
3 Practical Implementations of Speaker-Adaptive Training - Matsoukas, Schwartz, Jin, Nguyen (1997)(Correct)
Speaker Adaptive Training (SAT) has been shown to achieve
significant word error reductions relative to the common
Speaker Independent (SI) training paradigm, but its high requirements
in disk I/O and... / ultimate goal of automatic speech recognition has always been to achieve br relative to the common Speaker Independent SI training paradigm but
3 Utterance Clustering For Large Vocabulary Continuous Speech.. - Cook, Robinson (1995)(Correct)
Conventional speaker independent speech recognition systems
are trained using data from many different speakers.
Inter-speaker variability is a major problem because
parametric representations of spee... / Large Vocabulary Continuous Speech Recognition G.d. Cook And A.j. br ABSTRACT Conventional speaker independent speech recognition systems
3 Stochastic trajectory model analysis for accent classification - Angkititrakul, Hansen (1997)(Correct)
This paper presents recent results using statistics generated
by a MMI-supervised vector quantizer as a
measure of audio similarity. Such a measure has
proved successful for talker identification, and... / immediate applications for speech recognition in general there is no br The SSI large-vocabulary speaker-independent continuous-speech
3 A Phone-based Approach to Non-Linguistic Speech Feature Identification - Lamel, Gauvain (1995)(Correct)
In this paper we present a general approach to identifying non-linguistic speech features from the recorded
signal using phone-based acoustic likelihoods. The basic idea is to process the unknown spee... / Keywords continuous speech recognition speaker-identification br models from the set of speaker-independent acoustic models so as to
3 Towards Improved Speech Recognition Using A Speech Production Model - Blackburn, Young (1995)(Correct)
Considerable improvement in the performance of continuous
speech recognition systems, particularly those based
on Hidden Markov Models (HMMs), has been shown in recent
years. Nevertheless a number of ... / Towards Improved Speech Recognition Using A Speech Production br male speaker taken from the speaker-dependent portion of the Defence
3 Cross-Lingual Experiments with Phone Recognition - Lamel, Gauvain(Correct)
This paper presents some of the recent research on speaker-independent
continuous phone recognition for both French and English. The phone
accuracy is assessed on the BREF corpus for French, and on th... / and evaluation of automatic speech recognition systems. TIMIT contains a br of the recent research on speaker-independent continuous phone
3 Tangerine : A Large Vocabulary Mandarin Dictation System - Yuqing Gao Hsiao-Wuen (1995)(Correct)
this paper new features and improvements to the dictation
system are presented. The new features and improvements have produced an overall reduction in
recognition error of 50 - 80%. The vocabulary ha... / using large vocabulary speech recognition provides a convenient mode br it is very important for a speaker-dependent speech recognition system to
3 A Continuous-Speech Interface to a DecisionSupport System: I.. - Smadar Shiffman Ms (1994)(Correct)
Objective: Develop a continuous-speech interface that allows flexible input of
clinical findings into a medical diagnostic application.
Design: Our program allows users to enter clinical findings usin... / includes two components a speechrecognition component that converts br a specific speaker whereas speaker-independent systems accept input from
3 The SRI Telephone-based ATIS System - Bratt, Dowding, Hunicke-Smith (1995)(Correct)
The telephone-based ATIS system developed at SRI International is composed of the DECIPHER 1 speech recognition system, Gemini natural language understanding system, and Entropic's TrueTalk text-to-sp... / of the DECIPHER speech recognition system Gemini natural br version of SRI's DECIPHER speaker-independent continuous speech
3 Experiments on Sentence Boundary Detection - Stevenson, Gaizauskas (2000)(Correct)
This paper explores the problem of identifying sentence boundaries in the transcriptions produced by
automatic speech recognition systems. An experiment which determines the level of human performance... / produced by automatic speech recognition systems. An experiment which br large vocabulary tasks and speaker-independent systems WER varies between
3 Using High Level Dialogue Information For Dialogue Act Recognition.. - Wright, Poesio, Isard (1999)(Correct)
We look at the effect of using high level discourse knowledge in dialogue act type detection. We also look at ways this knowledge can be used for improving language modelling and intonation modelling ... / also be used in automatic speech recognition systems to improve word br Set I.e. The System Is Speaker Independent. . System Architecture
3 Recognition Of Non-Native Accents - Teixeira, Trancoso, Serralheiro (1997)(Correct)
This paper deals with the problem of non-native
accents in speech recognition. Reference tests were
performed using whole-word and sub-word models
trained either with a native accent or a pool of nati... / of non-native accents in speech recognition. Reference tests were br can be viewed as a speaker independent recognition problem for
3 Speaker Adaptation In Continuous Speech Recognition Via Estimation Of .. - Rozzi (1991)(Correct)
The present study addressed the problem of speaker adaptation in both feature-based and
stochastic model-based continuous speech recognition systems. Effective speaker adaptation
procedures must be ab... / Adaptation In Continuous Speech Recognition Via Estimation Of br extensive training current speaker-independent recognition systems may
3 Factoring Networks By A Statistical Method - Morgan, Bourlard (1992)(Correct)
INTRODUCTION Both on theoretical and practical grounds, it is generally preferable to reduce the number of parameters for a trainable classifier system. In particular, it would be desirable to factor ... / continuous speech recognition where it is being used to br applying this approach to speaker-independent continuous speech
3 Applying Large Vocabulary Hybrid HMM-MLP Methods to Telephone.. - Ma (1995)(Correct)
The hybrid Hidden Markov Model (HMM) / Neural Network (NN) speech recognition
system at the International Computer Science Institute (ICSI) uses a single
hidden layer MLP (Multi Layer Perceptron) to c... / HMM Neural Network NN speech recognition system at the International br on small vocabulary size speaker-independent task is compared with
3 New Ways To Use LVQ-Codebooks Together With Hidden Markov Models - Torkkola (1994)(Correct)
We introduce a novel way to employ codebooks trained by Learning Vector Quantization together with hidden Markov models. In previous work, LVQ-codebooks have been used as frame labelers. The resulting... / techniques in automatic speech recognition with well studied and br Katagiri and E. McDermott. Speaker independent large vocabulary word
3 Spoken Dialogue Management Using Probabilistic Reasoning - Roy, Pineau, Thrun (2000)(Correct)
Spoken dialogue managers have benefited from stochastic planners such as MDPs. However, so far, MDPs do not handle well noisy and ambiguous speech utterances. We use a POMDP-style approach to generate... / managers and show that as speech recognition degrades the POMDP br interaction. Speech recognition and speech understanding however
3 Concept-to-Speech Synthesis by Phonological Structure Matching - Taylor (2000)(Correct)
This paper presents a new way of generating synthetic speech waveforms from a linguistic description. The algorithm is presented as a proposed solution to the speech generation problem in a concept-to... / processing. For example in speech recognition there has been a very br word low vocabulary tasks to speaker-independent large vocabulary
3 Variance Compensation Within The MLLR Framework For Robust Speech.. - Gales, Pye, Woodland (1996)(Correct)
This paper investigates the use of maximum likelihood linear regression
(MLLR) for both speaker and environment adaptation. MLLR
transforms the mean and variance parameters of a set of HMMs.
In this p... / Mllr Framework For Robust Speech Recognition And Speaker Adaptation br on large vocabulary speaker independent data sets are described. On
3 Voice Command II: A DSP Implementation of Robust Speech Recognition.. - Soo-Young Lee Doh-Suk (1997)(Correct)
The "Voice Command" system, designed for isolated word
recognition tasks in real-world noisy environments, was implemented
on a fixed-point DSP board to operate in real-time.
Simple auditory model, i.... / DSP Implementation of Robust Speech Recognition in Real-World Noisy br Voice Command for speaker-independent small vocabulary speech
3 List of Figures - Distribution Tying For(Correct)
Models for Linear Dynamic Systems", Electron. Syst. Lab, M.I.T., Cambridge, MA,
Rep. ESL-R-814, 1978.
[31] R. H. Shumway and D. S. Stoffer, "An Approach to Time Series Smoothing and
Forecasting Using... / with Applications to Speech Recognition IEEE TraC s. oC br K. F. Lee and H. W. Hon Speaker-independent Phone Recognition Using
3 Connectionist Probability Estimation in HMM Speech Recognition - Renals, Morgan (1992)(Correct)
This report is concerned with integrating connectionist networks into a hidden Markov
model (HMM) speech recognition system, This is achieved through a statistical understanding
of connectionist netwo... / Estimation in HMM Speech Recognition Steve Renals and Nelson br Estimated Training Recognition Speech Features Estimated
3 A Similarity Measure for Automatic Audio Classification - Foote (1997)(Correct)
This paper presents recent results using statistics generated
by a MMI-supervised vector quantizer as a
measure of audio similarity. Such a measure has
proved successful for talker identi#cation, a... / immediate applications for speech recognition in general there is no br The SSI large-vocabulary speaker-independent continuous-speech
3 Prototype-Based Minimum Classification Error / Generalized.. - McDermott, Katagiri (1994)(Correct)
In previous work we reported high classification rates for Learning Vector Quantization (LVQ)
networks trained to classify phoneme tokens shifted in time. It has since been shown that the
framework of... / is not usually the goal of speech recognition and even if done br S.McDermott E. Speaker-Independent Large Vocabulary Word
2 Talking Vs Taking: Speech Access To Remote Computers - Yankelovich (1994)(Correct)
INTRODUCTION Have you ever been in a rush to go to a meeting and realized halfway there that you forgot to print out the mail message with all the location information? For times like these, remote ac... / to remote access by using speech recognition. To this end the project br SPARCstation with the Hark speaker-independent continuous recognizer
2 The GlobalPhone Project: Multilingual LVCSR with JANUS-3 - Schultz, Westphal, Waibel (1997)(Correct)
This paper describes our recent effort in developing the GlobalPhone database for multilingual large vocabulary continuous speech recognition. In particular we present the current status of the Glob... / large vocabulary continuous speech recognition. In particular we present br and testing large vocabulary speaker-independent speech recognition systems
2 City Name Recognition Over The Telephone - Fanty, Schmid, Cole (1993)(Correct)
We present a neural-network-based speech recognition system
for telephone speech. A neural network classifier provides
phoneme probabilities for each frame of the utterance.
A dynamic programming algo... / a neural-network-based speech recognition system for telephone br Our goal is to produce speaker-independent rapidlyconfigurable e.g.
2 Developments in Continuous Speech Dictation using the ARPA WSJ Task - L.Gauvain, Lamel, Adda-Decker(Correct)
In this paper we report on our recent development work in large
vocabulary,American English continuous speech dictation. We have
experimented with (1) alternative analyses for the acoustic front end,
... / speaker-independent SI speech recognition of read-speech. The test br Research in large vocabulary speaker-independent dictation at LIMSI
2 ASL: Architectures for Speech and Language Processing - Menzel (1993)(Correct)
Further advances in speech recognition heavily depend on the design of architectures which are flexible enough to accomodate very different requirements for the flow of data and hypotheses. These requ... / Further advances in speech recognition heavily depend on the br became to a certain degree speaker independent ones and nowadays even
2 The Speech-Language Interface In The Spoken Language Translator - Carter, Rayner (1994)(Correct)
The Spoken Language Translator (SLT) is a prototype
for practically useful systems capable of
translating continuous spoken language within restricted
domains. The prototype system translates
air trav... / gives a brief overview of the speech recognition and language analysis parts br of SRI's DECIPHER TM speaker-independent continuous speech
2 SpeechActs: A Framework for Building Speech Applications - Yankelovich, Baatz (1994)(Correct)
this paper; however, the basic technique involves creating patterns comprised of subpatterns that deal with classes of words. Individual words are kept in lexicons and tagged with many types of inform... / from the grammar and the speech recognition output into application br Instruments. These are both speaker-independent continuous speech