Title:
Mandarin Chinese Tone Recognition Based on Hyper-rectangular Fuzzy System

Authors:
Chih-Hsu Hsu, Taiwan

Abstract:

This paper presents a multi-resolution feature extraction technique to Mandarin Chinese tone recognition. The proposed multi-resolution feature extraction technique uses wavelet transform and wavelet packet to calculate features of each sub-band in order not to spread noise distortions over the entire feature space. In our previous works, we had developed a method for speech classification. For speech classification, the universe of discourse is divided into many types, and each type is treated as a class. The hyper-rectangular fuzzy system is used to classify frames and integrate the rule-based approach. The variances of each sub-band are utilized to extract both crisp and fuzzy classification rules. Mandarin Chinese tone recognition involves identifying and distinguishing between four tones. Accurate tone recognition is vital for language understanding systems because tones carry lexical meaning.  In our experiments, the Chinese corpus is used and extracts features of tones. The effectiveness of the proposed system is encouraging.

DOI: http://dx.doi.org/10.51505/ijaemr.2025.1418