James Glass, Jane Chang, Michael McCandless  Home/Search
Context Related
| mikemccandless.com/icslp96.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: mikemccandless.com/pubs (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)
Similar documents based on text: More All
0.2: A Probabilistic Framework For Feature-Based Speech.. - Glass, Chang, McCandless (1996) (Correct)
0.1: On Phonology-Syntax Interfaces - Sakamoto (Correct)
0.1: A Model for Interactive Computation: Applications to Speech.. - McCandless (1998) (Correct)
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/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/glass96probabilistic.html" }
Citations (may not include all citations):68 Speaker-independent phone recognition using hidden Markov mo.. (context) - Lee, Hon - 1989
57 Speech database development: design and analysis of the acou.. (context) - Lamel, Kassel et al. - 1986
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
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 Several improvements to a recurrent error propagation phone .. (context) - Robinson - 1991
13 High accuracy phone recognition using context clustering and.. (context) - Ljolje - 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 A second-order HMM for high performance word and phoneme-bas.. (context) - Mari, Fohr et al. - 1996
7 Speech recognition using stochastic segment neural networks (context) - Leung, Hetherington et al. - 1992
6 Stochastic segment modelling using the Estimate-Maximize alg.. (context) - Roucos, Ostendorf et al. - 1988
[Article contains additional citations not shown here]
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.mikemccandless.com/pubs.html): More
The Technology - An Effective Network (Correct)
Integrating Natural Language Into The Word Graph Search.. - Seneff, McCandless, Zue (1995) (Correct)
Internet Services Internet Services - Believe That One (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