%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 06:04:55 PM

@INPROCEEDINGS{eurospeech01,
         author = {Morris, Andrew and Hagen, Astrid and Bourlard, Herv{\'{e}}},
       keywords = {missing data, multi-band, multi-band combination, multi-stream, robust ASR},
       projects = {Idiap},
          title = {MAP Combination of Multi-Stream HMM or HMM/ANN Experts},
      booktitle = {Proc. Eurospeech},
           year = {2001},
        address = {Aalborg, Denmark},
       crossref = {morris-rr-01-14},
       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.},
            pdf = {https://publications.idiap.ch/attachments/reports/2001/morris-2001-eurospeech.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2001/morris-2001-eurospeech.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{morris-RR-01-14,
         author = {Morris, Andrew and Hagen, Astrid and Bourlard, Herv{\'{e}}},
       keywords = {missing data, multi-band, multi-band combination, multi-stream, robust ASR},
       projects = {Idiap},
          title = {MAP Combination of Multi-Stream HMM or HMM/ANN Experts},
           type = {Idiap-RR},
         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.},
            pdf = {https://publications.idiap.ch/attachments/reports/2001/rr01-14.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2001/rr01-14.ps.gz},
ipdmembership={speech},
}