Crosslingual Tandem-SGMM: Exploiting Out-Of-Language Data for Acoustic Model and Feature Level Adaptation
| Type of publication: | Idiap-RR |
| Citation: | Motlicek_Idiap-RR-39-2013 |
| Number: | Idiap-RR-39-2013 |
| Year: | 2013 |
| Month: | 11 |
| 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. |
| Keywords: | Acoustic model adaptation, Automatic Speech Recognition, under-resourced languages |
| Projects |
Idiap DBOX SNSF-MULTI |
| Authors | |
| Crossref by |
Motlicek_INTERSPEECH2013_2013 |
| Added by: | [ADM] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
