Methods for task adaptation of acoustic models with limited transcribed in-domain data
8th International Conference on Spoken Language Processing, ICSLP 2004, Jeju, Jeju Island, Güney Kore, 4 - 08 Ekim 2004, ss.2953-2956, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Basıldığı Şehir: Jeju, Jeju Island
- Basıldığı Ülke: Güney Kore
- Sayfa Sayıları: ss.2953-2956
- Boğaziçi Üniversitesi Adresli: Evet
Özet
Application specific acoustic models provide the best recognition accuracy, but they are expensive to train, because they require the transcription of tens or hundreds of hours of in-domain speech. Therefore, this paper focuses on the acoustic model estimation given limited in-domain transcribed speech data, and large amounts of (typically available) transcribed out-of-domain data. First, we evaluate several combinations of known methods to optimize the adaptation/training of acoustic models on the limited in-domain speech data. Then, we propose to use Gaussian sharing to combine in-domain models with out-of-domain models, and a data generation process to simulate the presence of more speakers in the in-domain data. In a spoken language dialog application, we contrast our methods against an upper accuracy bound of 69.1% (model trained on many in-domain data) and a lower bound of 60.8% (no in-domain data). Using only 2 hours of in-domain speech for model estimation, we improve the accuracy by 5.1% (to 65.9%) over the lower bound; data generation and Gaussian sharing contribute 2.2% to this improvement. With 9 hours of in-domain speech, the improvement of accuracy is 6.5%, to 67.3%.