| 基于似然比测试的语音激活检测算法 |
| |
| 引用本文： | 李燕诚,崔慧娟,唐昆.基于似然比测试的语音激活检测算法[J].计算机工程,2009,35(10):214-216. |
| |
| 作者姓名： | 李燕诚 崔慧娟 唐昆 |
| |
| 作者单位： | 清华大学电子工程系微波与数字通信技术国家重点实验室,北京,100084 |
| |
| 摘 要： | 针对低信噪比和噪声变化情况下语音激活检测算法性能下降的问题，提出一种新的参数更新和取值算法。该算法采用Laplacian-Gaussian混合模型对带噪语音频谱的概率分布进行建模，模型参数从带噪语音中估计得到，噪声功率参数通过跟踪语音的音节间隙进行平滑。实验结果表明，该算法在-5dB信噪比情况下，可以达到95％以上的检测率，具有优越的跟踪性能。
|
| 关 键 词： | 语音信号处理 语音激活检测 似然比测试 Laplacian-Gaussian混合模型 噪声跟踪 |
| 修稿时间： | |
Voice Activity Detection Algorithm Based on Likelihood Ratio Test |
| |
| LI Yan-cheng,CUI Hui-juan,TANG Kun.Voice Activity Detection Algorithm Based on Likelihood Ratio Test[J].Computer Engineering,2009,35(10):214-216. |
| |
| Authors: | LI Yan-cheng CUI Hui-juan TANG Kun |
| |
| Affiliation: | State Key Laboratory of Microwave and Digital Communications Technology;Department of Electronic Engineering;Tsinghua University;Beijing 100084 |
| |
| Abstract: | Aiming at the performance decline problem of voice activity detection under low signal-to-noise and noise change circumstances,this paper proposes a new parameter updating and value obtaining algorithm.This algorithm uses Laplacian-Gaussian mixed model,a new,efficient VAD algorithm using Likelihood Ratio Test(LRT) is proposed.The parameters of the model are estimated from noisy voice.The estimated noise power parameter is smoothed during the gaps of voice syllables.Experimental results indicate that the det... |
| |
| Keywords: | voice signal processing voice activity detection Likelihood Ratio Test(LRT) Laplacian-Gaussian mixed model noise tracking |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程》浏览原始摘要信息 |
|
点击此处可从《计算机工程》下载全文 |
