论文信息 - Unsupervised cross-lingual speaker adaptation for accented speech recognition

Unsupervised cross-lingual speaker adaptation for accented speech recognition

In this paper we present investigations on how the acoustic models in automatic speech recognition can be adapted across languages in unsupervised fashion to improve recognition of speech with a foreign accent. Recognition systems were trained on large Finnish and English corpora, and tested both on monolingual and bilingual material. Adaptation with bilingual and monolingual recognisers was compared. We found out that recognition of foreign accented English with help of Finnish adaptation training data from the same speaker was not improved significantly. However, the recognition of native Finnish using foreign accented English adaptation data was improved significantly.

Mikko Kurimo | Reima Karhila

[1] Wayne H. Ward,et al. Issues in recognition of spanish-accented spontaneous english , 2003 .

[2] Yoshihiko Nankaku,et al. State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis , 2009, INTERSPEECH.

[3] Mark J. F. Gales,et al. Semi-tied covariance matrices for hidden Markov models , 1999, IEEE Trans. Speech Audio Process..

[4] Matthew Gibson. Two-pass decision tree construction for unsupervised adaptation of HMM-based synthesis models , 2009, INTERSPEECH.

[5] Tao Chen,et al. Accent Issues in Large Vocabulary Continuous Speech Recognition , 2004, Int. J. Speech Technol..

[6] Mikko Kurimo,et al. Importance of High-Order N-Gram Models in Morph-Based Speech Recognition , 2009, IEEE Transactions on Audio, Speech, and Language Processing.

[7] Katarina Bartkova,et al. On using units trained on foreign data for improved multiple accent speech recognition , 2007, Speech Commun..

[8] Harriet J. Nock,et al. Pronunciation modeling by sharing gaussian densities across phonetic models , 1999, EUROSPEECH.

[9] Harald Höge,et al. Foreign-accented speaker-independent speech recognition , 2004, INTERSPEECH.

[10] Qin Yan,et al. A comparative analysis of UK and US English accents in recognition and synthesis , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.