SCOPUS 정보 검색 플랫폼

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2001, Pages 173-176

Weighting schemes for audio-visual fusion in speech recognition

(5) Glotin, Hervé a Vergyri, Dimitru b Neti, Chulupathy c Potamianos, Gerusimos c Luettin, Juergen d

a France and IDIAP Martigny ^* (Switzerland)

b SRI INTERNATIONAL (United States)

c IBM T J WATSON RESEARCH CENTER (United States)

d Ascom Systec AG (Switzerland)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODELS; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION;

ACOUSTIC SIGNAL PROCESSING; ALGORITHMS; DATABASE SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; OPTIMIZATION; SIGNAL TO NOISE RATIO;

CONTINUOUS SPEECH RECOGNITION;

EID: 0034842451 PISSN: 15206149 EISSN: None Source Type: Journal
DOI: 10.1109/ICASSP.2001.940795 Document Type: Article

Times cited : (66)

References (17)

1
- 0034842342
- Asynchronous stream modeling for large vocabulary audio-visual speech recognition
- Proc. ICASSP, 2001
- Luettin, J.¹ Potamianos, G.² Neti, C.³

2
- 0003839976
- A measure of speech and pitch reliability from voicing
- F. Klassner, Ed.; Computational Auditory Scene Analysis (CASA) workshop
- (1999) Proc. Int. Joint Conf. on Artificial Intelligence (IJCAI) , pp. 61-70
- Berthommier, F.¹ Glotin, H.²

3
- 0002100804
- Adaptive determination of audio and visual weights for automatic speech recognition
- Proc. European Tutorial Workshop on Audio-Visual Speech Processing (AVSP), 1997 , pp. 61-64
- Rogozan, A.¹ Deléglise, P.² Alissali, M.³

4
- 0031625499
- Discriminative model combination
- Proc. ICASSP, 1998 , vol.1 , pp. 481-484
- Beyerlein, P.¹

5
- 0033690885
- Towards language independent acoustic modeling
- Proc. ICASSP, 2000 , vol.2 , pp. 1029-1032
- Beyerlein, P.¹ Byrne, W.² Huerta, J.M.³ Khudanpur, S.⁴ Marthi, B.⁵ Morgan, J.⁶ Pterek, N.⁷ Picone, J.⁸ Vergyri, D.⁹ Wang, W.¹⁰

6
- 85009113885
- Minimum risk acoustic clustering for multilingual acoustic model combination
- Proc. ICSLP, 2000 , vol.3 , pp. 873-876
- Vergyri, D.¹ Tsakalidis, S.² Byrne, W.³

7
- 0034853041
- Hierarchical discriminant features for audio-visual LVCSR
- Proc. ICASSP, 2001
- Potamianos, G.¹ Luettin, J.² Neti, C.³

8
- 0004052871
- Audio-visual speech recognition
- Tech. Rep., CLSP/Johns Hopkins University, Baltimore
- (2000)
- Neti, C.¹ Potamianos, G.² Luettin, J.³ Matthews, I.⁴ Glotin, H.⁵ Vergyri, D.⁶ Sison, J.⁷ Mashari, A.⁸ Zhou, J.⁹

9
- 0030355935
- A new ASR approach based on independent processing and recombination of partial frequency bands
- Proc. ICSLP, 1996 , vol.1 , pp. 426-429
- Bourland, H.¹ Dupont, S.²

10
- 0031624666
- Discriminative training of HMM stream exponents for audio-visual speech recognition
- Proc. ICASSP, 1998 , vol.6 , pp. 3733-3736
- Potamianos, G.¹ Graf, H.P.²

11
- 0034270644
- Audio-visual speech modeling for continuous speech recognition
- (2000) IEEE Transactions on Multimedia , vol.2 , Issue.3 , pp. 141-151
- Dupont, S.¹ Luettin, J.²

12
- 0000417467
- Visionary speech: Looking ahead to practical speechreading systems
- D. G. Stork and M. E. Hennecke, Eds.; Springer, Berlin
- (1996) Speechreading by Humans and Machines: Models, Systems and Applications , pp. 331-349
- Hennecke, M.E.¹ Stork, D.G.² Prasad, K.V.³

13
- 0001437767
- A new SNR-feature mapping for robust multistream speech recognition
- Proc. International Congress on Phonetic Sciences (ICPhS), 1999 , vol.1 , pp. 711-715
- Berthommier, F.¹ Glotin, H.²

14
- 0020319209
- Harmonic to noise ratio as an index of the degree of hoarseness
- (1982) Journal of the Acoustical Society of America , vol.1971 , pp. 1544-1550
- Yumoto, E.¹ Gould, W.J.² Baer, T.³

15
- 84960942890
- Test of several external posterior weighting functions for multiband full combination ASR
- Proc. ICSLP, 2000 , vol.1 , pp. 333-336
- Glotin, H.¹ Berthommier, F.²

16
- 0029725863
- Adaptive bimodal sensor fusion for automatic speechreading
- Proc. ICASSP, 1996 , vol.2 , pp. 833-836
- Meier, U.¹ Hurst, W.² Duchnowski, P.³

17
- 0003778719
- Ph.D. Thesis, CLSP/Johns Hopkins University, Baltimore
- (2000) Integration of Multiple Knowledge Sources in Speech Recognition Using Minimum Error Training
- Vergyri, D.¹

* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.