Weighted likelihood ratio (WLR) Hidden Markov Model for noisy speech recognition

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

Volumn 1, Issue , 2006, Pages

  Huang, Chao ^a   Huang, Yingchun ^a,b   Soong, Frank ^a   Zhou, Jianlai ^a  

^a MICROSOFT RESEARCH ASIA   (China)

^b INSTITUTE OF GEOLOGY AND GEOPHYSICS   (China)

Author keywords

[No Author keywords available]

Indexed keywords

DYNAMIC CEPSTRAL FEATURES; KERNELS; WEIGHTED LIKELIHOOD RATIO (WLR);

DATABASE SYSTEMS; PROBABILITY DENSITY FUNCTION; RESONANCE; ROBUSTNESS (CONTROL SYSTEMS); SIGNAL INTERFERENCE; SPEECH RECOGNITION;

HIDDEN MARKOV MODELS;

EID: 33947657054     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. Hams-Gunter Hirsch and David Pearce, "The Aurora Experimental Framework for the Performance Evaluation of Speech Recognition System under Noisy Conditions", Proc. of ISCA-ITRW ASR2000, pp.181-188, Sept. 2000.
2. Masahide SUGIYAMA, "LPC Spectral Matching Measures for Speech Recognition", Ph.D. dissertation, Tohoku Univ., Aug.1984.
3. Chen Yang, Frank S. Soong and Tan Lee, "Static and sDynamic Spectral Features: Their Noise Robustness and Optimal Weights for ASR", ICASSP2005, Philadelphia, USA.
4. The HTK Toolkit: http://htk.eng.cam.ac.uk.
5. Martin Cooke, Phil Green, Ljubomir Josifovski and Ascension Vizinho, "Robust Automatic Speech Recognition with Missing and Unreliable Acoustic Data", Speech Communication 34 (2001) pp. 267-285.
6. Douglas Ealey, Holly Kelleher and David Pearce, "Harmonic Tunneling: Tracking Non-station Noises during Speech", Eurospech'2001, Demark.