端点検出を行わない連続音声認識

抄録

A new continuous speech recognition method that does not need the explicit speech end-point detection is proposed. A one-pass decoding algorithm is modified to decode the input speech of infinite length so that, with appropriate non-speech models for silence and ambient noises, continuous speech recognition can be executed without the explicit end-point detection. The basic algorithm 1) decodes a processing block of the predetermined length, 2) tracebacks and finds the boundaries of the processing blocks where the word history in the preceding processing block is merged into one, and 3) restarts decoding from the boundary frame with the merged word history. The effectiveness of the method is verified by the spoken dialogue transcription experiments. With a 5-minute dialogue in a moving car, the proposed method gives better results in word accuracy than the results using the explicit end-point detection method and the conventional one-pass decoder.