Tone features in whispered Chinese.

Saved in:
Bibliographic Details
Title: Tone features in whispered Chinese.
Authors: Li Xueli1,2 lixueli@hotrrjail.com, Xu Boling1
Source: Progress in Natural Science. Mar2005, Vol. 15 Issue 3, p285-288. 4p.
Subjects: Tone (Phonetics), Speech, Phonetics, Speech perception, Sound, Chinese people
Abstract: Study on the whispered tone is important to speech recognition and conversion in whispered Chinese. In this paper, the characteristics of whispered speech are introduced and the tone features in whispered Chinese are discussed. There is no fundamental frequency in the whispered speech, so other features, such as the amplitude envelope, duration, glottal area, lip area, formant, and vocal tract length, are extracted and their contributions to the automatic tone recognition are compared. From the experiments with six simple Chinese whispered vowels in four tones, it is proved that loudness-weighted 32 Mel-frequency bands log-amplitude envelopes and duration can be used as the main tone features in the whispered Chinese tone recognition. The average tone recognition rate approaches that of the human perception level. [ABSTRACT FROM AUTHOR]
Copyright of Progress in Natural Science is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Study on the whispered tone is important to speech recognition and conversion in whispered Chinese. In this paper, the characteristics of whispered speech are introduced and the tone features in whispered Chinese are discussed. There is no fundamental frequency in the whispered speech, so other features, such as the amplitude envelope, duration, glottal area, lip area, formant, and vocal tract length, are extracted and their contributions to the automatic tone recognition are compared. From the experiments with six simple Chinese whispered vowels in four tones, it is proved that loudness-weighted 32 Mel-frequency bands log-amplitude envelopes and duration can be used as the main tone features in the whispered Chinese tone recognition. The average tone recognition rate approaches that of the human perception level. [ABSTRACT FROM AUTHOR]
ISSN:10020071