基于频域自适应动态压缩器的齿音抑制算法  

Tooth Sound Suppression Algorithm Based on Frequency Domain Adaptive Dynamic Compressor

作　　者：陈锦辉 CHEN Jinhui(FuJian I-Star Technology Co.,Ltd.,Fuzhou 350002,China)

机构地区：[1]福建星网智慧科技有限公司,福建福州530002

出　　处：《电声技术》2023年第4期72-74,85,共4页Audio Engineering

摘　　要：在免提通话系统中,当语音中含有“z,c,s,zh,ch,sh”等嘶嘶作响的声母时,气流在唇齿间摩擦产生齿音,这种刺耳的齿音会分散听者的注意力并导致听觉疲劳,最终影响通话体验。为了解决这一问题,基于动态压缩器提出了一种基于频域自适应压缩器的齿音抑制算法。该算法将语音信号从时域转换到频域,并将其划分为10个子频带。每个子频带分别经过自适应白化和动态压缩处理,以减弱齿音所在频段的能量。实验结果表明,相比于均衡器,基于频域自适应动态压缩器的齿音抑制算法在齿音的识别和抑制强度方面表现更优,同时对无齿音的时段和频段没有抑制作用,降低了语音的响度衰减。In the hands-free communication system,when the voice contains hissing initials such as“z,c,s,zh,ch,sh”,the airflow rubs between the lips and teeth,which will distract the listener and lead to hearing fatigue,and ultimately affect the communication experience.In order to solve this problem,based on the dynamic compressor,a tooth sound suppression algorithm based on the frequency domain adaptive compressor is proposed.The algorithm transforms the speech signal from time domain to frequency domain and divides it into 10 sub-bands.Each sub-band is subjected to adaptive whitening and dynamic compression to weaken the energy of the frequency band where the tooth sound is located.The experimental results show that,compared with the equalizer,the tooth sound suppression algorithm based on frequency domain adaptive dynamic compressor performs better in the identification and suppression intensity of tooth sound,and has no suppression effect on the period and frequency band without tooth sound,which reduces the loudness attenuation of speech.

关 键 词：齿音抑制 动态压缩器 自适应白化 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]