%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 01:14:10 PM

@INPROCEEDINGS{weber-ar-00-42-01,
         author = {Weber, Katrin and Bengio, Samy and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          month = {9},
          title = {{HMM2}- Extraction of {F}ormant {F}eatures and their Use for {R}obust {ASR}},
      booktitle = {European Conference on Speech Communication and Technology (Eurospeech 2001)},
           year = {2001},
        address = {Aalborg, Denmark},
           note = {IDIAP-rr 00-42},
       crossref = {weber-rr-00-42},
       abstract = {As recently introduced, an HMM2 can be considered as a particular case of an HMM mixture in which the HMM emission probabilities (usually estimated through Gaussian mixtures or an artificial neural network) are modeled by state-dependent, feature-based HMM (referred to as frequency HMM). A general EM training algorithm for such a structure has already been developed. Although there are numerous motivations for using such a structure, and many possible ways to exploit it, this paper will mainly focus on one particular instantiation of HMM2 in which the frequency HMM will be used to extract formant structure information, which will then be used as additional acoustic features in a standard Automatic Speech Recognition (ASR) system. While the fact that this architecture is able to automatically extract meaningful formant information is interesting by itself, empirical results will also show the robustness of these features to noise, and their potential to enhance regular HMM-based ASR.},
            pdf = {https://publications.idiap.ch/attachments/reports/2000/rr00-42.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2000/rr00-42.ps.gz},
ipdmembership={speech},
language={English},
}



crossreferenced publications: 
@TECHREPORT{weber-rr-00-42,
         author = {Weber, Katrin and Bengio, Samy and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          title = {{HMM2}- Extraction of {F}ormant {F}eatures and their Use for {R}obust {ASR}},
           type = {Idiap-RR},
         number = {Idiap-RR-42-2000},
           year = {2000},
    institution = {IDIAP},
        address = {Martigny, Switzerland},
           note = {Published: Eurospeech 2001, Aalborg},
       abstract = {As recently introduced, an HMM2 can be considered as a particular case of an HMM mixture in which the HMM emission probabilities (usually estimated through Gaussian mixtures or an artificial neural network) are modeled by state-dependent, feature-based HMM (referred to as frequency HMM). A general EM training algorithm for such a structure has already been developed. Although there are numerous motivations for using such a structure, and many possible ways to exploit it, this paper will mainly focus on one particular instantiation of HMM2 in which the frequency HMM will be used to extract formant structure information, which will then be used as additional acoustic features in a standard Automatic Speech Recognition (ASR) system. While the fact that this architecture is able to automatically extract meaningful formant information is interesting by itself, empirical results will also show the robustness of these features to noise, and their potential to enhance state-of-the-art noise-robust HMM-based ASR.},
            pdf = {https://publications.idiap.ch/attachments/reports/2000/rr00-42.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2000/rr00-42.ps.gz},
ipdinar={2000},
ipdmembership={speech},
language={English},
}