LIÊN KẾT WEBSITE
Unsupervised acoustic model adaptation for multi-origin non native ASR
Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 Số , năm 2010 (Tập , trang 254-257)
DOI:
Tài liệu thuộc danh mục: Scopus
Conference Paper
English
Từ khóa: Acoustic model adaptation; Acoustic modeling; Different origins; Language recognition; Multilingual acoustic modeling; Multilingual acoustic models; Non-native; Non-native ASR; Speech recognition systems; Unsupervised adaptation; Interpolation; Speech communication; Telephone sets; Telephone systems; Speech recognition
Tóm tắt tiếng anh
To date, the performance of speech and language recognition systems is poor on non-native speech. The challenge for non-native speech recognition is to maximize the accuracy of a speech recognition system when only a small amount of non-native data is available. We report on the acoustic model adaptation for improving the recognition of non-native speech in English, French and Vietnamese, spoken by speakers of different origins. Using online unsupervised adaptation acoustic modeling without any additional data for adapting purposes, we investigate how an unsupervised multilingual acoustic model interpolation method can help to improve the phone accuracy of the system. Results improvement of 7% of absolute phone level accuracy (PLA) obtained from the experiments demonstrate the feasibility of the method. � 2010 ISCA.
