%Aigaion2 BibTeX export from Idiap Publications
%Thursday 02 May 2024 01:55:29 AM

@INPROCEEDINGS{Motlicek_INTERSPEECH2013_2013,
         author = {Motlicek, Petr and Imseng, David and Garner, Philip N.},
       projects = {Idiap, DBOX, SNSF-MULTI},
          month = aug,
          title = {Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation},
      booktitle = {Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013)},
           year = {2013},
          pages = {510-514},
      publisher = {ISCA},
       location = {Lyon, France},
   organization = {ISCA - International Speech Communication Association},
           issn = {2308-457X},
       crossref = {Motlicek_Idiap-RR-39-2013},
       abstract = {Recent studies have shown that speech recognizers may benefit from data in languages other than the target language through efficient acoustic model- or feature-level adaptation. Crosslingual Tandem-Subspace Gaussian Mixture Models (SGMM) are successfully able to combine acoustic model- and feature-level adaptation techniques. More specifically, we focus on under-resourced languages (Afrikaans in our case) and perform feature-level adaptation through the estimation of phone class posterior features with a Multilayer Perceptron that was trained
on data from a similar language with large amounts of available speech data (Dutch in our case). The same Dutch data can also be exploited on an acoustic model-level by training globally-shared SGMM parameters in a crosslingual way. The
two adaptation techniques are indeed complementary and result in a crosslingual Tandem-SGMM system that yields relative improvement of about 22\% compared to a standard speech recognizer on an Afrikaans phoneme recognition task.  Interestingly, eventual score-level combination of the individual SGMM systems yields additional 3\% relative improvement.},
            pdf = {https://publications.idiap.ch/attachments/papers/2013/Motlicek_INTERSPEECH2013_2013.pdf}
}



crossreferenced publications: 
@TECHREPORT{Motlicek_Idiap-RR-39-2013,
         author = {Motlicek, Petr and Imseng, David and Garner, Philip N.},
       keywords = {Acoustic model adaptation, Automatic Speech Recognition, under-resourced languages},
       projects = {Idiap, DBOX, SNSF-MULTI},
          month = {11},
          title = {Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation},
           type = {Idiap-RR},
         number = {Idiap-RR-39-2013},
           year = {2013},
    institution = {Idiap},
        address = {Rue Marconi 19, Martigny, Switzerland},
       abstract = {Recent studies have shown that speech recognizers may benefit from data in languages other than the target language through efficient acoustic model- or feature-level adaptation. Crosslingual Tandem-Subspace Gaussian Mixture Models (SGMM) are successfully able to combine acoustic model- and feature-level adaptation techniques. More specifically, we focus on under-resourced languages (Afrikaans in our case) and perform feature-level adaptation through the estimation of phone class posterior features with a Multilayer Perceptron that was trained
on data from a similar language with large amounts of available speech data (Dutch in our case). The same Dutch data can also be exploited on an acoustic model-level by training globally-shared SGMM parameters in a crosslingual way. The two adaptation techniques are indeed complementary and result in a crosslingual Tandem-SGMM system that yields relative improvement of about 22\% compared to a standard speech recognizer on an Afrikaans phoneme recognition task. Interestingly, eventual score-level combination of the individual SGMM systems yields additional 3\% relative improvement.},
            pdf = {https://publications.idiap.ch/attachments/reports/2013/Motlicek_Idiap-RR-39-2013.pdf}
}