INTERSPEECH 2010
11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Speech Recognition Using Long-Term Phase Information

Kazumasa Yamamoto, Eiichi Sueyoshi, Seiichi Nakagawa

Toyohashi University of Technology, Japan

Current speech recognition systems use mainly amplitude spectrum-based features such as MFFC for acoustic feature parameters, while discarding phase spectral information. The results of perceptual experiments, however, suggested that phase spectral information based on long-term analysis includes certain linguistic information. In this paper, we propose the use of phase features based on long-term analysis for speech recognition. We use two types of parameters: the delta phase parameter as a group delay and analytic group delay features. Isolated word and continuous digit recognition experiments were performed, resulting in a greater than 90% word or digit accuracy for each of the experiments. The experimental results confirmed that a long-term phase spectrum includes sufficient information for recognizing speech. Furthermore, combining likelihoods of MFCC and long-term group delay cepstrum outperformed the baseline MFCC relatively 20% for clean speech.

Full Paper

Bibliographic reference.  Yamamoto, Kazumasa / Sueyoshi, Eiichi / Nakagawa, Seiichi (2010): "Speech recognition using long-term phase information", In INTERSPEECH-2010, 1189-1192.