移动通信2016，Vol.40Issue(14)：25-28,4.DOI:10.3969/j.issn.1006-1010.2016.14.005
基于长时子带能量变化特征的语音活动检测
Voice Activity Detection Based on Long-Term Sub-Band Energy Variability Feature
李宝岩1
作者信息
- 1. 吉林吉大通信设计院股份有限公司，吉林 长春 130012
- 折叠
摘要
Abstract
Concerning the issue that the reliability of the current voice activity detection (VAD) algorithm is difficult to guarantee at low signal-to-noise ratio (SNR) conditions, this paper presented the measure of long-term sub-band energy variability to capture the sub-band energy of short-time spectrum varying over time. The performance of the feature was evaluated using Gaussian mixture models (GMMs) on the TIMIT corpus. Experimental results showed the accuracy of the proposed VAD scheme was better than that obtained by the traditional VAD schemes under ifve types of noises and different SNR conditions.关键词
语音活动检测/长时子带能量/高斯混合模型Key words
voice activity detection/long-term sub-band energy/Gaussian mixture models (GMMs)分类
信息技术与安全科学引用本文复制引用
李宝岩..基于长时子带能量变化特征的语音活动检测[J].移动通信,2016,40(14):25-28,4.
