Adaptive ML-weighting in multi-band recombination of gaussian mixture ASR

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

Volumn 1, Issue , 2001, Pages 257-260

  Hagen, A ^a,b   Bourlard, H ^a   Morris, A ^a  

^a EPFL   (Switzerland)

^b IDIAP RESEARCH INSTITUTE   (Switzerland)

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; GAUSSIAN MIXTURE MODEL; RECOMBINATION PROCESS;

ACOUSTIC NOISE; ITERATIVE METHODS; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PROBABILITY DISTRIBUTIONS; SIGNAL TO NOISE RATIO; SPEECH ANALYSIS; VECTORS;

SPEECH RECOGNITION;

EID: 0034854717     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.940816     Document Type: Article

References (8)

1. Recognising occluded speech
2. Using mutual information to design feature combinations
3. Comparison of HMM experts with MLP experts in the full combination multi-band approach to robust ASR
4. From multi-band full combination to multi-stream full combination processing in robust ASR
5. Towards asr on partially corrupted speech
6. Multi-stream adaptive evidence combination to noise robust ASR