论文信息 - The COST 278 MASPER Initiative - Crosslingual Speech Recognition with Large Telephone Databases

The COST 278 MASPER Initiative - Crosslingual Speech Recognition with Large Telephone Databases

This paper presents the work on crosslingual speech recognition carried out by the MASPER initiative that was formed as a part of the COST 278 Action. Two different approaches for transfering monolingual source acoustic models to a new language were compared. The first one was expert-driven, based on the IPA scheme. The second was data-driven, based on a crosslingual phoneme confusion matrix. German, Spanish, Hungarian and Slovak were used as sourcelanguages. Slovenian was selected to be the target language. All experiments were carried out on SpeechDat databases. The results’ analysis showed that the expert-driven method outperforms the data-driven one, and that similarities between source and target language have a significant influence on the performance.

[1] Narada D. Warakagoda,et al. The COST 249 SpeechDat Multilingual Reference Recogniser , 2000, LREC.

[2] Lou Boves,et al. Annotation in the SpeechDat Projects , 2001, Int. J. Speech Technol..

[3] Jan Cernocký,et al. Speechdat-e: five eastern european speech databases for voice-operated teleservices completed , 2001, INTERSPEECH.

[4] Narada D. Warakagoda,et al. A Noise Robust Multilingual Reference Recogniser Based on Speechdat(II) , 2000, INTERSPEECH.

[5] Tanja Schultz. Multilinguale Spracherkennung: Kombination akustischer Modelle zur Portierung auf neue Sprachen , 2001 .

[6] Richard Winski,et al. European speech databases for telephone applications , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.