%Aigaion2 BibTeX export from Idiap Publications %Saturday 21 December 2024 07:23:19 PM @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} }