Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Phoneme Recognition Based on Fisher Weight Map to Higher-Order Local Auto-Correlation

Yasuo Ariki, Shunsuke Kato, Tetsuya Takiguchi

Kobe University, Japan

In this paper, we propose a new feature extraction method based on higher-order local auto-correlation (HLAC) and Fisher weight map (FWM). Widely used MFCC features lack temporal dynamics. To solve this problem, 35 types of local auto-correlation features are computed within two-dimensional local regions. These local features are accumulated over more global regions by weighting high scores on the discriminative areas where the typical features among all phonemes are well expressed. This score map is called Fisher weight map. We verified the effectiveness of the HLAC and FWM through vowel recognition and total phoneme recognition.

Full Paper

Bibliographic reference.  Ariki, Yasuo / Kato, Shunsuke / Takiguchi, Tetsuya (2006): "Phoneme recognition based on fisher weight map to higher-order local auto-correlation", In INTERSPEECH-2006, paper 1883-Mon2BuP.9.