메뉴 건너뛰기




Volumn 25, Issue 2, 2011, Pages 440-461

Topic tracking language model for speech recognition

Author keywords

Language model; Latent topic model; On line algorithm; Speech recognition; Topic tracking

Indexed keywords

CHANGING ENVIRONMENT; CORPUS OF SPONTANEOUS JAPANESE; INCREMENTAL TRACKING; LANGUAGE FEATURES; LANGUAGE MODEL; LANGUAGE MODEL ADAPTATION; LATENT TOPIC MODEL; ON CURRENTS; ON-LINE ALGORITHM; REAL ENVIRONMENTS; SPEAKING STYLES; TEXT INFORMATION; TOPIC MODEL; TOPIC TRACKING; TRACK CHANGES;

EID: 78049521179     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2010.07.006     Document Type: Article
Times cited : (29)

References (38)
  • 1
    • 85009142125 scopus 로고    scopus 로고
    • Language model adaptation based on PLSA of topics and speakers
    • Y. Akita, and T. Kawahara Language model adaptation based on PLSA of topics and speakers Proc. ICSLP'04 2004 1045 1048
    • (2004) Proc. ICSLP'04 , pp. 1045-1048
    • Akita, Y.1    Kawahara, T.2
  • 3
    • 0000274403 scopus 로고    scopus 로고
    • Exploiting latent semantic information in statistical language modeling
    • J. Bellegarda Exploiting latent semantic information in statistical language modeling Proceedings of IEEE 88 8 2000 1279 1296
    • (2000) Proceedings of IEEE , vol.88 , Issue.8 , pp. 1279-1296
    • Bellegarda, J.1
  • 4
    • 0346008165 scopus 로고    scopus 로고
    • Statistical language model adaptation: Review and perspectives
    • J. Bellegarda Statistical language model adaptation: review and perspectives Speech Communication 42 1 2004 93 108
    • (2004) Speech Communication , vol.42 , Issue.1 , pp. 93-108
    • Bellegarda, J.1
  • 7
  • 9
    • 0030351557 scopus 로고    scopus 로고
    • Bayesian estimation methods of n-gram language model adaptation
    • M. Federico Bayesian estimation methods of n-gram language model adaptation Proc. ICSLP'96 1996 240 243
    • (1996) Proc. ICSLP'96 , pp. 240-243
    • Federico, M.1
  • 10
    • 34547508186 scopus 로고    scopus 로고
    • Noise robust voice activity detection based on statistical model and parallel non-linear Kalman filtering
    • M. Fujimoto, K. Ishizuka, and H. Kato Noise robust voice activity detection based on statistical model and parallel non-linear Kalman filtering Proc. ICASSP'07. Vol. 4 2007 797 800
    • (2007) Proc. ICASSP'07. Vol. 4 , pp. 797-800
    • Fujimoto, M.1    Ishizuka, K.2    Kato, H.3
  • 11
    • 33745207361 scopus 로고    scopus 로고
    • A Japanese national project on spontaneous speech corpus and processing technology
    • S. Furui, K.H. Maekawa, and M. Isahara A Japanese national project on spontaneous speech corpus and processing technology Proc. ASR'00 2000 244 248
    • (2000) Proc. ASR'00 , pp. 244-248
    • Furui, S.1    Maekawa, K.H.2    Isahara, M.3
  • 12
    • 85121030057 scopus 로고    scopus 로고
    • Topic-based language models using em
    • D. Gildea, and T. Hofmann Topic-based language models using EM Proc. Eurospeech'99 1999 2167 2170
    • (1999) Proc. Eurospeech'99 , pp. 2167-2170
    • Gildea, D.1    Hofmann, T.2
  • 17
    • 0001509519 scopus 로고    scopus 로고
    • Probabilistic latent semantic analysis
    • T. Hofmann Probabilistic latent semantic analysis Proc. UAI'99 1999 289 296
    • (1999) Proc. UAI'99 , pp. 289-296
    • Hofmann, T.1
  • 19
    • 60949090683 scopus 로고    scopus 로고
    • World-wide media browser - Multilingual audio-visual content retrieval and browsing system
    • T. Hori, K. Sudoh, H. Tsukada, and A. Nakamura World-wide media browser - multilingual audio-visual content retrieval and browsing system NTT Technical Review 7 2 2009
    • (2009) NTT Technical Review , vol.7 , Issue.2
    • Hori, T.1    Sudoh, K.2    Tsukada, H.3    Nakamura, A.4
  • 20
    • 80053341989 scopus 로고    scopus 로고
    • Style & topic language model adaptation using HMMLDA
    • B.J. Hsu, and J. Glass Style & topic language model adaptation using HMMLDA Proc. EMNLP 2006 2006 373 381
    • (2006) Proc. EMNLP 2006 , pp. 373-381
    • Hsu, B.J.1    Glass, J.2
  • 21
    • 84867201512 scopus 로고    scopus 로고
    • Unsupervised language model adaptation based on topic and role information in multiparty meeting
    • S. Huang, and S. Renals Unsupervised language model adaptation based on topic and role information in multiparty meeting Proc. Interspeech'08 2008 833 836
    • (2008) Proc. Interspeech'08 , pp. 833-836
    • Huang, S.1    Renals, S.2
  • 22
    • 77956207114 scopus 로고    scopus 로고
    • Topic tracking model for analyzing consumer purchase behavior
    • T. Iwata, S. Watanabe, T. Yamada, and N. Ueda Topic tracking model for analyzing consumer purchase behavior Proc. IJCAI'09 2009 1427 1432
    • (2009) Proc. IJCAI'09 , pp. 1427-1432
    • Iwata, T.1    Watanabe, S.2    Yamada, T.3    Ueda, N.4
  • 24
    • 0030369272 scopus 로고    scopus 로고
    • Modeling long distance dependence in language: Topic mixtures vs. dynamic cache models
    • R. Iyer, and M. Ostendorf Modeling long distance dependence in language: topic mixtures vs. dynamic cache models Proc. ICSLP'96, vol. 1 1996 236 239
    • (1996) Proc. ICSLP'96, Vol. 1 , pp. 236-239
    • Iyer, R.1    Ostendorf, M.2
  • 25
    • 85022925778 scopus 로고    scopus 로고
    • Language model adaptation using dynamic marginals
    • R. Kneser, J. Peters, and D. Klakow Language model adaptation using dynamic marginals Proc. Eurospeech'97 1997 1971 1974
    • (1997) Proc. Eurospeech'97 , pp. 1971-1974
    • Kneser, R.1    Peters, J.2    Klakow, D.3
  • 29
    • 0141596527 scopus 로고    scopus 로고
    • Estimating a Dirichlet distribution
    • Minka, T., 2000. Estimating a Dirichlet distribution. Tech. rep., MIT.
    • (2000) Tech. Rep., MIT
    • Minka, T.1
  • 30
    • 78049488169 scopus 로고    scopus 로고
    • Evaluation of the SOLON speech recognition system: 2006 benchmark using the Corpus of Spontaneous Japanese
    • A. Nakamura, T. Oba, S. Watanabe, K. Ishizuka, M. Fujimoto, T. Hori, E. Mc-Dermott, and Y. Minami Evaluation of the SOLON speech recognition system: 2006 benchmark using the Corpus of Spontaneous Japanese IPSJ SIG Notes 2006 136 2006 251 256 (in Japanese)
    • (2006) IPSJ SIG Notes , vol.2006 , Issue.136 , pp. 251-256
    • Nakamura, A.1    Oba, T.2    Watanabe, S.3    Ishizuka, K.4    Fujimoto, M.5    Hori, T.6    Mc-Dermott, E.7    Minami, Y.8
  • 31
    • 85009274873 scopus 로고    scopus 로고
    • Unsupervised language model adaptation for lecture speech transcription
    • T. Niesler, and D. Willett Unsupervised language model adaptation for lecture speech transcription Proc. Interspeech'02 2002 1413 1416
    • (2002) Proc. Interspeech'02 , pp. 1413-1416
    • Niesler, T.1    Willett, D.2
  • 33
    • 33646907991 scopus 로고    scopus 로고
    • Two decades of statistical language modeling: Where do we go from here
    • R. Rosenfeld Two decades of statistical language modeling: where do we go from here Proceedings of IEEE 88 8 2000 1270 1278
    • (2000) Proceedings of IEEE , vol.88 , Issue.8 , pp. 1270-1278
    • Rosenfeld, R.1
  • 36
    • 33749245495 scopus 로고    scopus 로고
    • Topic modeling: Beyond bag-of-words
    • H.M. Wallach Topic modeling: beyond bag-of-words Proc. ICML'06 2006 977 984
    • (2006) Proc. ICML'06 , pp. 977-984
    • Wallach, H.M.1
  • 37
    • 80053284667 scopus 로고    scopus 로고
    • Continuous time dynamic topic models
    • C. Wang, D. Blei, and D. Heckerman Continuous time dynamic topic models Proc. UAI'08 2008 579 586
    • (2008) Proc. UAI'08 , pp. 579-586
    • Wang, C.1    Blei, D.2    Heckerman, D.3
  • 38
    • 84880859170 scopus 로고    scopus 로고
    • Dynamic mixture models for multiple timeseries
    • X. Wei, J. Sun, and X. Wang Dynamic mixture models for multiple timeseries Proc. IJCAI'07 2007 2909 2914
    • (2007) Proc. IJCAI'07 , pp. 2909-2914
    • Wei, X.1    Sun, J.2    Wang, X.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.