Investigations on exemplar-based features for speech recognition towards thousands of hours of unsupervised, noisy data

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

Volumn , Issue , 2012, Pages 4437-4440

  Heigold, Georg ^a   Nguyen, Patrick ^a   Weintraub, Mitchel ^a   Vanhoucke, Vincent ^a  

^a GOOGLE INC   (United States)

Author keywords

conditional random fields; Exemplar based speech recognition; speech recognition

Indexed keywords

ACOUSTIC MODEL; BASE-LINE PERFORMANCE; COMPUTATIONAL POWER; CONDITIONAL RANDOM FIELD; LONG SPAN; MASSIVE DATA; MODELING APPROACH; NOISY DATA; SPEECH RECOGNITION SYSTEMS; WORD LEVEL; YOUTUBE;

HIDDEN MARKOV MODELS; SIGNAL PROCESSING;

SPEECH RECOGNITION;

EID: 84867584256     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2012.6288904     Document Type: Conference Paper

References (10)

1. O. Ghitza and M. Mohan Sondhi, "Hidden Markov models with templates as non-stationary states: an application to speech recognition," Computer Speech and Language, vol. 2, pp. 101-119, 1993.
2. M. De Wachter et al., "Template-based continuous speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 15, no. 4, pp. 1377-1390, 2007.
3. S. Axelrod and B. Maison, "Combination of hidden Markov models with dynamic time warping for speech recognition," in Proc. ICASSP, Montreal, Quebec, Canada, May 2004, pp. 173-176.
4. G. Zweig et al., "Speech recognition with segmental conditional random fields: A summary of the JHU CSLP 2010 summer workshop," in Proc. ICASSP, Prague, Czech Republic, May 2011, pp. 5044-5047.
5. T.N. Sainath et al., "Exemplar-based sparse representation features: From TIMIT to LVCSR," IEEE Transactions on Speech and Audio Processing, vol. 19, no. 8, pp. 2598-2613, 2011.
6. G. Heigold et al., "A flat direct model for speech recognition," in Proc. ICASSP, Taipei, Taiwan, Apr. 2009, pp. 3861-3864.
7. G. Zweig and P. Nguyen, "A segmental CRF approach to large vocabulary continuous speech recognition," in Proc. ASRU, Merano, Italy, Dec. 2009, pp. 152-157.
8. B. Hoffmeister et al., "Cross-site and intra-site ASR system combination: Comparisons on lattice and 1-best methods," in Proc. ICASSP, Honolulu, HI, USA, Apr. 2007, pp. 1145-1148.
9. G. Heigold, R. Schlüter, and H. Ney, "Modified MPE/MMI in a transducer-based framework," in Proc. ICASSP, Taipei, Taiwan, Apr. 2009, pp. 3749-3752.
10. S. Chen and R. Rosenfeld, "A Gaussian prior for smoothing maximum entropy models," Technical Report CMUCS-99-108, Computer Science Department, Carnegie Mellon University, 1999.