Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Lex Olorenshaw"'
Publikováno v:
International Journal of Speech Technology. 10:63-74
In this paper we discuss two techniques to reduce the size of the acoustic model while maintaining or improving the accuracy of the recognition engine. The first technique, demiphone modeling, tries to reduce the redundancy existing in a context depe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b323e35a77e20392a3cf6a96f9b2437d
https://doi.org/10.1007/s10772-008-9012-6
https://doi.org/10.1007/s10772-008-9012-6
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5e98f616825be18b9eeabb0086674868
https://doi.org/10.21437/interspeech.2004-455
https://doi.org/10.21437/interspeech.2004-455
Publikováno v:
INTERSPEECH
Scopus-Elsevier
Scopus-Elsevier
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd89a8b53b1c018f87df61d6f92662ff
https://doi.org/10.21437/interspeech.2004-183
https://doi.org/10.21437/interspeech.2004-183
Publikováno v:
ICASSP
This paper describes a novel noise robust speech detection algorithm that can operate reliably in severe noisy car conditions. High performance has been obtained with the following techniques: (1) noise suppression based on principal component analys
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e99d2a0e3e5ff05f06a3a1109f6b51ca
https://doi.org/10.1109/icassp.1999.758424
https://doi.org/10.1109/icassp.1999.758424
Publikováno v:
5th International Conference on Spoken Language Processing (ICSLP 1998).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc9682032ab6ceadd33e0155b47c1520
https://doi.org/10.21437/icslp.1998-284
https://doi.org/10.21437/icslp.1998-284
Publikováno v:
The Journal of the Acoustical Society of America. 128:516
The present invention comprises a system and method for implementing a Cantonese speech recognizer with an optimized phone set, and may include a recognizer configured to compare input speech data to phone strings from a vocabulary dictionary that is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e1691bdf33e60cdbf58c9e30f2330fef
https://doi.org/10.1121/1.3472334
https://doi.org/10.1121/1.3472334
Publikováno v:
The Journal of the Acoustical Society of America. 128:516
The present invention comprises a system and method for implementing a Mandarin Chinese speech recognizer with an optimized phone set (610), and may include a recognizer configured to compare input speech data to phone strings from a vocabulary dicti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e3197e313e5373d0f6cd25bd2e27c731
https://doi.org/10.1121/1.3472335
https://doi.org/10.1121/1.3472335
Publikováno v:
The Journal of the Acoustical Society of America. 126:3386
A system and method for effectively performing speech recognition procedures includes enhanced demiphone acoustic models that a speech recognition engine utilizes to perform the speech recognition procedures. The enhanced demiphone acoustic models ea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a2c75a0d8ecf01d13de42376f4efce4b
https://doi.org/10.1121/1.3274300
https://doi.org/10.1121/1.3274300
Autor:
Lex Olorenshaw, Xavier Menendez-Pidal
Publikováno v:
The Journal of the Acoustical Society of America. 119:2568
The present invention comprises a methodology for implementing a vocabulary set for use in a speech recognition system, and may preferably include a recognizer for analyzing utterances from the vocabulary set to generate N-best lists of recognition c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f9ba826491cd9db6cdcc4771606e440
https://doi.org/10.1121/1.2203576
https://doi.org/10.1121/1.2203576
Publikováno v:
The Journal of the Acoustical Society of America. 117:3361
A system and method for speech verification using out-of-vocabulary models includes a speech recognizer that has a model bank with system vocabulary word models, a garbage model, and one or more noise models. The model bank may reject an utterance or
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d37f6bd712c2ab750202a9f73402ec2f
https://doi.org/10.1121/1.1948288
https://doi.org/10.1121/1.1948288