Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Yen-Lu Chow"'
Autor:
M. Dunham, J. Makhoul, S. Roucos, Yen-Lu Chow, Patti Price, Owen Kimball, M. Krasner, Richard Schwartz, Francis Kubala
Publikováno v:
ICASSP
This paper describes the results of our work in designing a system for large-vocabulary word recognition of continuous speech. We generalize the use of context-dependent Hidden Markov Models (HMM) of phonemes to take into account word-dependent coart
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::373d044e5ba11792428666cc242c3be8
https://doi.org/10.1109/icassp.1986.1168931
https://doi.org/10.1109/icassp.1986.1168931
Publikováno v:
ICASSP
This paper deals with rapid speaker adaptation for speech recognition. We introduce a new algorithm that transforms hidden Markov models of speech derived from one "prototype" speaker so that they model the speech of a new speaker. The Speaker normal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::89e10c53879b7124c0913c123a2fd0f4
https://doi.org/10.1109/icassp.1987.1169575
https://doi.org/10.1109/icassp.1987.1169575
Autor:
Richard Schwartz, G. Kubala, S. Roucos, John Makhoul, Owen Kimball, M. Krasner, Patti Price, M. Dunham, Yen-Lu Chow
Publikováno v:
ICASSP
In this paper, we describe BYBLOS, the BBN continuous speech recognition system. The system, designed for large vocabulary applications, integrates acoustic, phonetic, lexical, and linguistic knowledge sources to achieve high recognition performance.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::944fdd46b81b35b59818202a53bd6786
https://doi.org/10.1109/icassp.1987.1169748
https://doi.org/10.1109/icassp.1987.1169748
Publikováno v:
ICASSP
Statistical language models have been successfully used to improve the performance of continuous speech recognition algorithms. Application of such techniques is difficult when only a small training corpus is available. The authors present an approac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9e80134b1320263a15011faeda68bc54
https://doi.org/10.1109/icassp.1988.196567
https://doi.org/10.1109/icassp.1988.196567
Autor:
Ming-Whei Feng, Yen-Lu Chow, J. Makhoul, R. Schwartz, J. Vandegrift, A Derr, S. Roucos, J.R. Rohlicek, Francis Kubala, Patti Price, Owen Kimball
Publikováno v:
ICASSP
The system was trained in a speaker dependent mode on 28 minutes of speech from each of 8 speakers, and was tested on independent test material for each speaker. The system was tested with three artificial grammars spanning a broad perplexity range.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c45c49290ca3708040adbbd15dbea12
https://doi.org/10.1109/icassp.1988.196573
https://doi.org/10.1109/icassp.1988.196573
Publikováno v:
ICASSP
A new approach is proposed for the clustering of words in a given vocabulary. The method is based on a paradigm first formulated in the context of information retrieval, called latent semantic analysis. This paradigm leads to a parsimonious vector re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d18b10625de2868c9b5299eae44928ea
https://doi.org/10.1109/icassp.1996.540318
https://doi.org/10.1109/icassp.1996.540318
Publikováno v:
ICASSP (1)
Although commercial dictation products are beginning to emerge for English, the existence of a convenient keyboard has prevented pervasive use of dictation. On the other hand, for non alphabetic languages like Chinese, there is no convenient input me
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d17a007749521893e651e6c70f554b8
https://doi.org/10.1109/icassp.1994.389236
https://doi.org/10.1109/icassp.1994.389236
Publikováno v:
ICASSP
This paper focuses on the architecture design, implementation and optimisation of distributed speech recognition systems. Client-server DSR architecture is presented based on the analysis of alternative architectures and an integrated prototype syste
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::46148417ca08767574027152b758cbe4
https://doi.org/10.1109/icassp.2000.861880
https://doi.org/10.1109/icassp.2000.861880
Publikováno v:
HLT
We present a 1000-word continuous speech recognition (CSR) system that operates in real time on a personal computer (PC). The system, designed for large vocabulary natural language tasks, makes use of phonetic Hidden Markov models (HMM) and incorpora
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c75a8d596928a55eaf23e876cb17394
https://doi.org/10.3115/116580.116610
https://doi.org/10.3115/116580.116610
Publikováno v:
The Journal of the Acoustical Society of America. 104:3159
A system and method for performing speaker adaptation in a speech recognition system which includes a set of reference models corresponding to speech data from a plurality of speakers. The speech data is represented by a plurality of acoustic models
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f6f79e47e4c8e5917ec0c1d0b9d488b1
https://doi.org/10.1121/1.423984
https://doi.org/10.1121/1.423984