Mandarin Tone Recognition Based on Pre-Classification

Author

Tang, Lin ; Yin, Junxun

Author_Institution

Dept. of Inf. Technol., Jiangmen Polytech.

Volume

2

fYear

0

fDate

0-0 0

Firstpage

9468

Lastpage

9472

Abstract

Mandarin tone behavior varies greatly from speaker to speaker and it is this that presents the greatest challenge to any speaker-independent tone recognition system. This paper presents a speaker normalizing algorithm which is designed to reduce this influence. In addition to this, the other tone variations are pre-classified into four categories: the neutral tone, and the isolated syllable, the disyllable and the polysyllable. The neutral tone is a special tonal sandhi, and the recognition rate of the neutral tone is poor in many current tone recognition systems. So, this paper proposes a special treatment for the neutral tone. The experimental results show that by using these new methods, an accuracy rate of 96.64% can be achieved in Mandarin tone recognition

Keywords

natural languages; pattern classification; speech recognition; Mandarin tone recognition; disyllable; isolated syllable; neutral tone; polysyllable; speaker normalizing algorithm; speech recognition; Algorithm design and analysis; Artificial neural networks; Educational institutions; Hidden Markov models; Information technology; Natural languages; Neural networks; Speech recognition; Training data; Vector quantization; Speech recognition; Tone recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on

Conference_Location

Dalian

Print_ISBN

1-4244-0332-4

Type

conf

DOI

10.1109/WCICA.2006.1713835

Filename

1713835