A nonlinear observation model for removing noise from corrupted speech log mel-spectral energies

7th International Conference on Spoken Language Processing, ICSLP 2002

Volumn , Issue , 2002, Pages 1569-1572

  Droppo, Jasha ^a   Acero, Alex ^a   Deng, Li ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADDITIVE NOISE; CRIME; SPEECH COMMUNICATION; SPEECH RECOGNITION;

AUTOMATIC SPEECH RECOGNITION; FEATURE DIMENSIONS; LOW DIMENSIONALITY; OBSERVATION MODEL; SPECTRAL FEATURE; SPECTRAL SUBTRACTIONS; STATISTICAL MODELING; TUNING PARAMETER; CLEAN SPEECH; HIDDEN VARIABLE; MEL FREQUENCIES; NOISE ROBUST; REMOVING NOISE; SPECTRAL ENERGY; STATISTIC MODELING;

SPEECH RECOGNITION; ADDITIVE NOISE;

EID: 85009211607     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (2)

1. H. G. Hirsch and D. Pearce, "The AURORA experimental framework for the performance evaluations of speech recognition systems under noisy condidions", in ISCA ITRW ASR2000 "Automatic Speech Recognition: Challenges for the Next Millennium", Paris, France, September 2000.
2. J. Droppo, A. Acero, and L. Deng, "Uncertainty decoding with SPLICE for noise robust speech recognition", in Proc. 2002 ICASSP, Orlando, Florida, May 2002.