计算机科学
耳机
估计员
水准点(测量)
语音识别
语音活动检测
噪音(视频)
能量(信号处理)
数字信号处理器
可靠性(半导体)
信噪比(成像)
背景噪声
数字信号处理
实时计算
人工智能
语音处理
工程类
功率(物理)
数学
计算机硬件
电信
统计
物理
电气工程
图像(数学)
量子力学
地理
大地测量学
作者
Narimene Lezzoum,Ghyslain Gagnon,Jérémie Voix
出处
期刊:IEEE Transactions on Consumer Electronics
[Institute of Electrical and Electronics Engineers]
日期:2014-11-01
卷期号:60 (4): 737-744
被引量:18
标识
DOI:10.1109/tce.2014.7027350
摘要
This paper presents a real-time voice activity detection (VAD) algorithm implemented in a miniature Digital Signal Processor (DSP) for in-ear listening devices such as earphones or headphones. This system allows consumers to hear external speech signals such as public announcements or oral communication while listening to music without removing their listening devices. The proposed algorithm uses two normalized energy features that compare the energy in the frequency region containing speech information with the frequency regions typically containing noise. The extraction of the normalized features represents the key of the proposed VAD since it eliminates the need for a signal-to-noise ratio (SNR) estimator. The VAD's decision is made using two threshold comparison rules computed from the normalized features and a hangover scheme triggered after a given number of observations. The algorithm parameters, namely the frequency regions' boundaries, number of observations, two decision thresholds and hangover's duration, have been optimized offline using a genetic algorithm. The performance of the proposed VAD is compared to a benchmark algorithm in four noise environments and three SNRs. Results show that the average false positive rate (FPR) of the proposed algorithm is 4.2% and the average true positive rate (TPR) is 91.4 % compared to the benchmark algorithm which has a FPR average of 29.9 % and a TPR average of 79.0 %. The proposed VAD is implemented in hardware to validate its reliability and complexity.
科研通智能强力驱动
Strongly Powered by AbleSci AI