James Glass, Jane Chang, Michael McCandless  Home/Search
Context Related
| mit.edu/sls/archiv...icslp96summit.pdf udel.edu/icslp/cdrom/vol4/76...a768.pdf Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: mit.edu/sls/archives/root...index (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Most current speech recognizers use an observation space which is based on a temporal sequence of "frames" (e.g., Mel-cepstra). There is another class of recognizer which further processes these frames to produce a segment-based network, and represents each segment by fixed-dimensional "features." In such feature-based recognizers the observation space takes the form of a temporal network of feature vectors, so that a single segmentation of an utterance will use a subset of all possible feature ... (Update)
Cited by: More
Using Acoustic-Phonetic Information - John-Paul Hosom University (Correct)
Automatic Continuous Speech Recognition with Rapid Speaker.. - Ström (1997) (Correct)
Segment-Based Recognition on the PhoneBook Task: Initial.. - Livescu, Glass (2001) (Correct)
Similar documents (at the sentence level):
64.9%: A Probabilistic Framework For Feature-Based Speech.. - Glass, Chang, McCandless (1996) (Correct)
Active bibliography (related documents): More All
1.0: Near-Miss Modeling: A Segment-Based Approach to Speech Recognition - Chang (1998) (Correct)
0.9: Statistical Trajectory Models for Phonetic Recognition - Goldenthal (1994) (Correct)
0.4: Probabilistic Segmentation for Segment-Based Speech Recognition - Lee (1998) (Correct)
Similar documents based on text: More All
0.1: BucketTree: Improving Collision Detection Between.. - Ganovelli.. (2000) (Correct)
0.1: Feature Detection and Identification using a Sonar-Array - Araujo, Grupen (1998) (Correct)
0.1: A Comparison of Two Range-Based Pose Estimators for a . . . - Shaffer, al. (1992) (Correct)
Related documents from co-citation: More All
23: JUPITER: A telephone-based conversational interface for weather information - Zue - 2000
21: Realtime Telephone-based Speech Recognition in the Jupiter Domain - Glass, Hazen et al. - 1999
14: Multilingual spoken language understanding in the MIT VOYAGER system - Glass, Flammia et al. - 1995
BibTeX entry: (Update)
J. Glass, J. Chang, and M. McCandless. A probabilistic framework for featurebased speech recognition. In Proc. ICSLP, 1996. http://citeseer.ist.psu.edu/article/glass96probabilistic.html More
@inproceedings{ glass96probabilistic,
author = "J. Glass and J. Chang and M. McCandless",
title = "A Probabilistic Framework for Feature-based Speech Recognition",
booktitle = "Proc. {ICSLP} '96",
volume = "4",
address = "Philadelphia, PA",
pages = "2277--2280",
year = "1996",
url = "citeseer.ist.psu.edu/article/glass96probabilistic.html" }
Citations (may not include all citations):97 An application of recurrent nets to phone probability estima.. - Robinson - 1994
68 Speaker-independent phone recognition using hidden Markov mo.. (context) - Lee, Hon - 1989
43 A stochastic segment model for phonemebased continuous speec.. (context) - Ostendorf, Roucos - 1989
38 ML estimation of a stochastic linear system with the EM algo.. - Digilakis, Rohlicek et al. - 1993
35 A hidden Markov model based keyword recognition system (context) - Rose, Paul - 1990
33 High performance speaker-independent phone recognition using.. - Lamel, Gauvain - 1993
33 The DARPA TIMIT acoustic-phonetic continuous speech corpus C.. (context) - Garofolo, Lamel et al. - 1990
30 Automatic recognition of keywords in unconstrained speech us.. (context) - Wilpon, Rabiner et al. - 1990
23 Statistical trajectory models for phonetic recognition - Goldenthal - 1994
18 State clustering in hidden Markov modelbased continuous spee.. (context) - Young, Woodland - 1994
13 High accuracy phone recognition using context clustering and.. (context) - Ljolje - 1994
11 IPA: Improved phone modelling with recurrent neural networks (context) - Robinson, Hochberg et al. - 1994
10 SAPPHIRE: An extensible speech analysis and recognition tool.. - Hetherington, McCandless
10 Recent progress on the SUMMIT system (context) - Zue, Glass et al. - 1990
7 Speech recognition using stochastic segment neural networks (context) - Leung, Hetherington et al. - 1992
7 A second-order HMM for high performance word and phoneme-bas.. (context) - Mari, Fohr et al. - 1996
6 Stochastic segment modelling using the Estimate-Maximize alg.. (context) - Roucos, Ostendorf et al. - 1988
5 Phonetic recognition in a segment-based HMM (context) - Marcus - 1993
5 Modeling speech variability with segmental HMMs (context) - Holmes, Russell - 1996
5 Phonetic transition modelling for continuous speech recognit.. (context) - Phillips, Glass - 1994
4 Continuous hidden Markov modelling for speaker-independent w.. (context) - Rohlicek, Russell et al. - 1989
3 Segmenting speech using dynamic programming (context) - Cohen - 1981
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.sls.lcs.mit.edu/sls/archives/root/publications/index.html): More
Hierarchical Duration Modelling for Speech Recognition Using.. - Chung, Seneff (1997) (Correct)
A Semi-Automatic System for the Syllabification and Stress.. - Parmar (1997) (Correct)
Real-Time Probabilistic Segmentation For Segment-Based Speech.. - Lee, Glass (1998) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC