%Aigaion2 BibTeX export from Idiap Publications
%Friday 05 December 2025 03:40:50 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}
}