Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (6): 1763-1768.DOI: 10.11772/j.issn.1001-9081.2019111880

• Network and communications • Previous Articles     Next Articles

Low SNR denoising algorithm based on adaptive voice activity detection and minimum mean-square error log-spectral amplitude estimation

ZHANG Haoran, WANG Xueyuan, LI Xiaoxia   

  1. Sichuan Key Laboratory of Special Environmental Robotics (School of Information Engineering, Southwest University of Science and Technology), Mianyang Sichuan 621010, China
  • Received:2019-11-05 Revised:2020-01-03 Online:2020-06-10 Published:2020-06-18
  • Contact: WANG Xueyuan, born in 1974, Ph. D., associate professor. His research interests include information processing.
  • About author:ZHANG Haoran, born in 1995, M. S. candidate. His research interests include signal processing, speech enhancement.WANG Xueyuan, born in 1974, Ph. D., associate professor. His research interests include information processing.LI Xiaoxia, born in 1976, Ph. D., professor. Her research interests include pattern recognition, computer vision.
  • Supported by:
    National Natural Science Foundation of China(61771411).

基于自适应阈值活动语音检测和最小均方误差对数谱幅度估计的低信噪比降噪算法

张皓然, 王学渊, 李小霞   

  1. 特殊环境机器人技术四川省重点实验室(西南科技大学 信息工程学院),四川 绵阳 621010
  • 通讯作者: 王学渊(1974—)
  • 作者简介:张皓然(1995—),男,四川绵阳人,硕士研究生,主要研究方向:信号处理、语音增强.王学渊(1974—),男,四川绵阳人,副教授,博士,主要研究方向:信息处理.李小霞(1976—),女,四川安岳人,教授,博士,主要研究方向:模式识别、计算机视觉.
  • 基金资助:
    国家自然科学基金资助项目(61771411)。

Abstract: Aiming at the limitations of traditional noise reduction methods for acoustic signals in low Signal-to-Noise Ratio (SNR) environment, a real-time noise reduction algorithm was proposed by combining adaptive threshold Voice Activity Detection (VAD) algorithm and Minimum Mean-Square Error Log-Spectral Amplitude estimation (MMSE-LSA). Firstly, the background noise was estimated in VAD algorithm by probability statistics based on the maximum value of the energy probability, and the obtained background noise was updated in real time and saved. Then, the background noise updated in real time was used as the reference noise of MMSE-LSA, and the noise amplitude spectrum was updated adaptively. Finally, the noise reduction processing was performed. The experimental results on four kinds of acoustic signals in real scenes show that the proposed algorithm can guarantee the real-time processing of low SNR acoustic signals; and compared with the traditional MMSE-LSA algorithm, it has the SNR of the noise reduction signal increased by 10-15 dB without over-subtraction. It can be applied to practical engineering.

Key words: real environment, adaptive threshold, Voice Activity Detection (VAD) algorithm, real-time Minimum Mean-Square Error Log-Spectral Amplitude estimation (MMSE-LSA) algorithm, real-time background, low Signal-to-Noise Ratio (SNR)

摘要: 针对低信噪比(SNR)环境下传统方法对声信号降噪的局限性,提出了一种联合自适应阈值活动语音检测(VAD)算法和最小均方误差对数谱幅度估计(MMSE-LSA)的实时降噪算法。首先,在VAD算法中通过基于能量概率最大值的概率统计来对背景噪声进行估计,对得到的背景噪声进行实时更新并保存;然后,将实时更新的背景噪声作为MMSE-LSA的参考噪声,并对噪声幅度谱进行自适应更新,最后进行降噪处理。通过在真实场景中对四类声信号进行实验,结果表明,该算法在保证对低SNR声信号的实时处理的情况下,相较于传统MMSE-LSA算法,降噪信号的SNR能够提高10~15 dB,且不存在信号过减的情况,可应用于实际工程。

关键词: 真实环境, 自适应阈值, 活动语音检测算法, 实时最小均方误差对数谱幅度估计算法, 实时背景, 低信噪比

CLC Number: