logo Idiap Research Institute        
 [BibTeX] [Marc21]
MAP Combination of Multi-Stream HMM or HMM/ANN Experts
Type of publication: Idiap-RR
Citation: morris-RR-01-14
Number: Idiap-RR-14-2001
Year: 2001
Institution: IDIAP
Abstract: Automatic speech recognition (ASR) performance falls dramatically with the level of mismatch between training and test data. The human ability to recognise speech when a large proportion of frequencies are dominated by noise has inspired the "missing data" and "multi-band" approaches to noise robust ASR. "Missing data" ASR identifies low SNR spectral data in each data frame and then ignores it. Multi-band ASR trains a separate model for each position of missing data, estimates a reliability weight for each model, then combines model outputs in a weighted sum. A problem with both approaches is that local data reliability estimation is inherently inaccurate and also assumes that all of the training data was clean. In this article we present a model in which adaptive multi-band expert weighting is incorporated naturally into the maximum a posteriori (MAP) decoding process.
Userfields: ipdmembership={speech},
Keywords: missing data, multi-band, multi-band combination, multi-stream, robust ASR
Projects Idiap
Authors Morris, Andrew
Hagen, Astrid
Bourlard, Hervé
Crossref by eurospeech01
Added by: [UNK]
Total mark: 0
  • rr01-14.pdf
  • rr01-14.ps.gz