Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Tadashi Emori"'
Autor:
Koichi Shinoda, Takafumi Koshinaka, Takuya Tsutaoka, Tadashi Emori, Yuzo Hamanaka, Sadaoki Furui
Publikováno v:
IEICE Transactions on Information and Systems. :2015-2023
We propose a committee-based method of active learning for large vocabulary continuous speech recognition. Multiple recognizers are trained in this approach, and the recognition results obtained from these are used for selecting utterances. Those utt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::38f3b0a23211721ec75023c7c067bb79
https://doi.org/10.1587/transinf.e94.d.2015
https://doi.org/10.1587/transinf.e94.d.2015
Autor:
Koichi Shinoda, Tadashi Emori
Publikováno v:
Systems and Computers in Japan. 33:30-40
Speaker normalization techniques for correcting differences in the vocal tract lengths of different speakers, referred to as vocal tract length normalization, in a large vocabulary voice recognition system using a hidden Markov model (HMM), have been
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::048a1fadfeb09d557142612a91b311d8
https://doi.org/10.1002/scj.1125
https://doi.org/10.1002/scj.1125
Publikováno v:
Interspeech 2012.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5fc13ffdfb3d0d51c945178da1ad356f
https://doi.org/10.21437/interspeech.2012-562
https://doi.org/10.21437/interspeech.2012-562
Publikováno v:
ICASSP
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the recognition results obtained from them are used for selecting utterances.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d442f68c35e1de05777b81d015abae15
https://doi.org/10.1109/icassp.2010.5495650
https://doi.org/10.1109/icassp.2010.5495650
Autor:
H. Hattori, Ken-ichi Iso, Akitoshi Okumura, Shinichi Ando, Tadashi Emori, Ryosuke Isotani, Kiyoshi Yamabana, Takao Watanabe, Shinya Ishikawa, Ken Hanazawa
Publikováno v:
ICMI
We present an automatic speech-to-speech translation system for personal digital assistants (PDAs) that helps oral communication between Japanese and English speakers in various situations while traveling. Our original compact large vocabulary contin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c254cac2f198ff6dcf4c777d548fd582
https://doi.org/10.1109/icmi.2002.1166995
https://doi.org/10.1109/icmi.2002.1166995
Autor:
Tadashi Emori, Koichi Shinoda
Publikováno v:
7th European Conference on Speech Communication and Technology (Eurospeech 2001).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4430d1450f1531ebddf825257d54b2b5
https://doi.org/10.21437/eurospeech.2001-204
https://doi.org/10.21437/eurospeech.2001-204
Autor:
Koichi Shinoda, Tadashi Emori
Publikováno v:
The Journal of the Acoustical Society of America. 119:693
A voice recognition system comprises an analyzer for converting an input voice signal to an input pattern including cepstrum, a reference pattern for storing reference patterns, an elongation/contraction estimating unit for outputting an elongation/c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50611399ad8a522adfa27b9bef8068e9
https://doi.org/10.1121/1.2174527
https://doi.org/10.1121/1.2174527
Publikováno v:
Scopus-Elsevier
INTERSPEECH
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be44262d29fee265c716950b62bedb6d
http://www.scopus.com/inward/record.url?eid=2-s2.0-56149125455&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-56149125455&partnerID=MN8TOARS
