A robust compensation strategy for extraneous acoustic variations in spontaneous speech recognition.

We propose a robust compensation strategy to deal effectively with extraneous acoustic variations for spontaneous speech recognition. This strategy extends speaker adaptive training, and uses hidden Markov models (HMM) parameter transformations to normalize the extraneous variations in the training...

Descrición completa

Detalles Bibliográficos
Publicado en:	IEEE Transactions on speech and audio processing 10, 1 (2002).
Autor Principal:	Hui Jiang
Formato:	Artigo
Idioma:	English
Subjects:	Bayesian prediction classification. HMM parameter transformations. HMM system. Compact model. Conversational speech recognition. Extraneous acoustic variations. Generic model. Hidden Markov models. Inter-speaker variability. Maximum likelihood criterion. Prior PDF. Prior probability density functions. Pronunciation variations. Robust compensation. Robust decoding. Speaker adaptive training. Spontaneous speech recognition. Switchboard task. Telephone handset mismatch. Testing phase. Word error rate reduction. Word sequence.