Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation

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. Crosslin-gual 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 avail-able 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 im-provement of about 22 % compared to a standard speech recog-nizer on an Afrikaans phoneme recognition task. Interestingly, eventual score-level combination of the individual SGMM sys-tems yields additional 3 % relative improvement