Suppr超能文献

低频谐波对自然语音和语音编码语音音调识别的影响。

Effects of low harmonics on tone identification in natural and vocoded speech.

机构信息

Department of Communication Sciences and Disorders, University of Texas at Austin, 1 University Station A1100, Austin, Texas 78712, USA.

出版信息

J Acoust Soc Am. 2012 Nov;132(5):EL378-84. doi: 10.1121/1.4757729.

Abstract

This study investigated the contribution of low-frequency harmonics to identifying Mandarin tones in natural and vocoded speech in quiet and noisy conditions. Results showed that low-frequency harmonics of natural speech led to highly accurate tone identification; however, for vocoded speech, low-frequency harmonics yielded lower tone identification than stimuli with full harmonics, except for tone 4. Analysis of the correlation between tone accuracy and the amplitude-F0 correlation index suggested that "more" speech contents (i.e., more harmonics) did not necessarily yield better tone recognition for vocoded speech, especially when the amplitude contour of the signals did not co-vary with the F0 contour.

摘要

本研究旨在探究低频谐波在安静和嘈杂环境下识别自然和语音编码语音中普通话声调的作用。结果表明,自然语音的低频谐波能实现高度准确的声调识别;但对于语音编码语音,低频谐波的声调识别率低于全谐波刺激,除了 4 调。对声调识别准确率与音强-基频相关指数的相关性分析表明,语音编码语音中,“更多”的语音内容(即更多谐波)并不一定能带来更好的声调识别,尤其是当信号的振幅轮廓与基频轮廓不同步时。

相似文献

8
Comparison of fluctuating maskers for speech recognition tests.比较用于语音识别测试的波动掩蔽器。
Int J Audiol. 2011 Jan;50(1):2-13. doi: 10.3109/14992027.2010.505582. Epub 2010 Nov 23.
9
Relationship between speech recognition in noise and sparseness.噪声环境下语音识别与稀疏性的关系。
Int J Audiol. 2012 Feb;51(2):75-82. doi: 10.3109/14992027.2011.625984. Epub 2011 Nov 22.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验