舰船噪声环境下改进语音信号增强算法

doi:10.3969/j.issn.1001-2400.2016.05.024

西安电子科技大学学报

舰船噪声环境下改进语音信号增强算法

李大卫;杨日杰;韩建辉

(海军航空工程学院电子信息工程系，山东烟台 264001)

收稿日期:2015-07-05 出版日期:2016-10-20 发布日期:2016-12-02
通讯作者: 李大卫
作者简介:李大卫(1983-)，男，工程师，海军航空工程学院博士研究生，E-mail: latt68@sina.com．
基金资助:
国家自然科学基金资助项目(61271444)；“泰山学者”建设工程专项经费资助项目(2011)

Study of speech enhancement in the background of ship-radiated noise

LI Dawei;YANG Rijie;HAN Jianhui

(Dept. of Electronic and Information Engineering, Naval Aeronautical and Astronautical Univ., Yantai 264001, China)

Received:2015-07-05 Online:2016-10-20 Published:2016-12-02
Contact: LI Dawei

摘要/Abstract

摘要：

谱减法广泛应用于语音增强，但在舰船噪声环境下，噪声的复杂多样性给谱减法中信号的语音段与噪声段的正确检测带来极大的困难，影响了谱减法的效果，为此，笔者在分析信号频谱特性的基础上，首先通过分帧信号相邻帧间频谱的相似性测度对信号段粗判断，再利用帧间偏移方法进行精确判断，实现语音段与背景噪声段的精确辨别，进而利用谱减法实现舰船噪声环境下语音信号的增强．经过大量实测数据的验证，改进的谱减法能够适应多种类型舰船噪声环境下的语音增强，对语音段的判别准确度达到96％，对背景噪声的判别准确度达98％．与传统谱减法及其他相关改进算法相比，在低信噪比强背景噪声下，文中改进谱减法仍能取得稳定的语音增强效果．

关键词: 语音增强, 谱减法, 频谱相似性, 语音段检测, 帧间偏移

Abstract:

Spectral subtraction is wildly used in speech enhancement. But it is not always available in the ship working environment because of the fact that it is hard to discriminate the speech duration with the ship noise. So, in this paper, we propose a new approach, which first computes the frequency spectrum similarity and then discriminates the signal segments into speech or noise roughly. And then by the frame shifting method, we achieve a high discrimination precision. Finally, the improved algorithm is benchmarked on a large measured data and experimental results show that the proposed method can be used in various ship-radiated noise environments. The discrimination accuracy is 98％ for ship-radiated noise and 96％ for speech.

Key words: speech enhancement, spectral subtraction, spectrum similarity, speech detection, frame shifting

李大卫;杨日杰;韩建辉. 舰船噪声环境下改进语音信号增强算法[J]. 西安电子科技大学学报, 2016, 43(5): 133-138.

LI Dawei;YANG Rijie;HAN Jianhui. Study of speech enhancement in the background of ship-radiated noise[J]. Journal of Xidian University, 2016, 43(5): 133-138.

参考文献

［1］张君昌, 刘海鹏, 樊养余. 一种自适应时移与阈值的DCT语音增强算法［J］. 西安电子科技大学学报, 2014, 41(6): 155-159.
ZHANG Junchang, LIU Haipeng, FAN Yangyu. Speech Enhancement Method Using Self-adaptive Time-shift and Threshold Discrete Cosine Transform［J］. Journal of Xidian University, 2014, 41(6): 155-159.
［2］ RAMIREZ J, SEGURA J C, BENITEZ C, et al. Efficient Voice Activity Detection Algorithms Using Long-term Speech Information ［J］. Speech Communication, 2004, 42(3/4): 271-287.
［3］ MCCOWAN I, DEAN D, MCLAREN M, et al. The Delta-phase Spectrum with Application to Voice Activity Detection and Speaker Recognition ［J］. IEEE Transactions on Audio, Speech, and Language Processing, 2011, 19(7): 2026-2038.
［4］ PARK J, KIM J W, CHANG J H, et al. Estimation of Speech Absence Uncertainty based on Multiple Linear Regression Analysis for Speech Enhancement［J］. Applied Acoustics, 2015, 87: 205-211.
［5］ MOMENI H, ABUTALEBI H R, TADAION A. Joint Detection and Estimation of Speech Spectral Amplitude Using Noncontinuous Gain Functions［J］. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015, 23(8): 1249-1258.
［6］张君昌, 张丹, 崔力. 一种鲁棒自适应阈值的语音端点检测方法［J］. 西安电子科技大学学报, 2015, 42(5): 115-119.
ZHANG Junchang, ZHANG Dan, CUI Li. Robust Adaptive Threshold Speech Endpoint Detection Method ［J］. Journal of Xidian University, 2015, 42(5): 115-119.
［7］ KALAMANI M, VALARMATHY S, KRISHNAMOORTHI M. Speech Enhancement Using Modified Modulation Magnitude Estimation Based Spectral Subtraction Algorithm ［J］. Arabian Journal for Science and Engineering, 2014, 39(12): 8965-8978.
［8］ ZHANG Y, ZHAO Y X. Real and Imaginary Modulation Spectral Subtraction for Speech Enhancement ［J］. Speech Communication, 2013, 55(4): 509-522.
［9］ BSS Eval: a Toolbox for Performance Measurement in (Blind) Source Separation［EB/OL］. ［2015-06-12］. http://bass-db.gforge.inria.fr/bss_eval.
［10］ Singing Voice Separation: Demo Clips［EB/OL］. ［2015-06-12］. http://sites.google.com/site/unvoicedsoundseparation/mir-1K.
［11］ Music Information Retrieval Evaluation eXchange(MIREX)［EB/OL］. ［2015-06-12］. http://www.music-ir.org/mires/wiki/MIPEX_HOME.
［12］ MAK M W, YU H B. A Study of Voice Activity Detection Techniques for NIST Speaker Recognition Evaluations ［J］. Computer Speech and Language, 2014, 28(1): 295-313.
［13］ HSU C C, LIN T E, CHEN J H, et al. Voice Activity Detection Based on Frequency Modulation of Harmonics ［C］// Proceedings of 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing. Piscataway: IEEE, 2013: 6679-6683.

[1]	梅淑琳,贾海蓉,王晓刚,武奕峰. 动态特征联合新掩模优化神经网络语音增强[J]. 西安电子科技大学学报, 2021, 48(3): 91-98.
[2]	常新旭,张杨,杨林,寇金桥,王昕,徐冬冬. 融合多头自注意力机制的语音增强方法[J]. 西安电子科技大学学报, 2020, 47(1): 104-110.
[3]	袁文浩,梁春燕,娄迎曦,房超,王志强. 一种时频平滑的深度神经网络语音增强方法[J]. 西安电子科技大学学报, 2019, 46(4): 130-136.
[4]	贾海蓉,王卫梅,王雁,裴俊华. 区分性联合稀疏字典交替优化的语音增强[J]. 西安电子科技大学学报, 2019, 46(3): 74-81.
[5]	袁文浩,娄迎曦,梁春燕,王志强. 感知联合优化的深度神经网络语音增强方法[J]. 西安电子科技大学学报, 2019, 46(2): 89-94.
[6]	白静,史燕燕,薛珮芸,郭倩岩. 融合非线性幂函数和谱减法的CFCC特征提取[J]. 西安电子科技大学学报, 2019, 46(1): 86-92.
[7]	王栋;贾海蓉. 改进相位谱补偿的语音增强算法[J]. 西安电子科技大学学报, 2017, 44(3): 83-88.
[8]	郭欣;贾海蓉;王栋. 利用子空间改进的K-SVD语音增强算法[J]. 西安电子科技大学学报, 2016, 43(6): 109-115.
[9]	张君昌;刘海鹏;樊养余. 一种自适应时移与阈值的DCT语音增强算法[J]. J4, 2014, 41(6): 155-159+194.
[10]	曾庆宁;欧阳缮. 子带MCRASC-MGSC微型麦克风阵语音增强算法[J]. J4, 2010, 37(6): 1011-1016.

舰船噪声环境下改进语音信号增强算法

Study of speech enhancement in the background of ship-radiated noise

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

Metrics

本文评价

推荐阅读 10