SPEECH FEATURE EXTRACTION USING WEIGHTED HIGHER-ORDER LOCAL AUTO-CORRELATION

Yasuo Ariki (Japan), Tetsuya Takiguchi (Japan), Takashi Muroi (Japan) and Ryoichi Takashima (Japan)

Received June 16, 2009

Abstract

In this paper, we propose a new feature extraction method based on higher-order local auto-correlation (HLAC) and Fisher weight maps (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 placing high scores on the discriminative areas, where the typical features among all phonemes are well expressed. This score map is called a Fisher weight map. We verified the effectiveness of the HLAC and FWM through speaker-independent phoneme recognition. The proposed method showed an 82.1% recognition rate, 8.9 points higher than the result by MFCC. Furthermore, by combining the proposed feature with MFCC, MFCC and MFCC, the recognition rate improved to 86.6%. Experimental results also demonstrate the robustness of the proposed method in noisy environments in comparison with MFCC-based features.

Keywords and phrases: phoneme recognition, feature extraction, Fisher weight map, local auto-correlation.