A Real-Time Dual-Microphone Speech Enhancement Algorithm Assisted by Bone Conduction Sensor
The quality and intelligibility of the speech are usually impaired by the interference of background noise when using internet voice calls. To solve this problem in the context of wearable smart devices, this paper introduces a dual-microphone, bone-conduction (BC) sensor assisted beamformer and a s...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-09-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/18/5050 |
_version_ | 1797554486089089024 |
---|---|
author | Yi Zhou Yufan Chen Yongbao Ma Hongqing Liu |
author_facet | Yi Zhou Yufan Chen Yongbao Ma Hongqing Liu |
author_sort | Yi Zhou |
collection | DOAJ |
description | The quality and intelligibility of the speech are usually impaired by the interference of background noise when using internet voice calls. To solve this problem in the context of wearable smart devices, this paper introduces a dual-microphone, bone-conduction (BC) sensor assisted beamformer and a simple recurrent unit (SRU)-based neural network postfilter for real-time speech enhancement. Assisted by the BC sensor, which is insensitive to the environmental noise compared to the regular air-conduction (AC) microphone, the accurate voice activity detection (VAD) can be obtained from the BC signal and incorporated into the adaptive noise canceller (ANC) and adaptive block matrix (ABM). The SRU-based postfilter consists of a recurrent neural network with a small number of parameters, which improves the computational efficiency. The sub-band signal processing is designed to compress the input features of the neural network, and the scale-invariant signal-to-distortion ratio (SI-SDR) is developed as the loss function to minimize the distortion of the desired speech signal. Experimental results demonstrate that the proposed real-time speech enhancement system provides significant speech sound quality and intelligibility improvements for all noise types and levels when compared with the AC-only beamformer with a postfiltering algorithm. |
first_indexed | 2024-03-10T16:32:46Z |
format | Article |
id | doaj.art-5e192cd982f2487888274be549f5bb37 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T16:32:46Z |
publishDate | 2020-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-5e192cd982f2487888274be549f5bb372023-11-20T12:42:38ZengMDPI AGSensors1424-82202020-09-012018505010.3390/s20185050A Real-Time Dual-Microphone Speech Enhancement Algorithm Assisted by Bone Conduction SensorYi Zhou0Yufan Chen1Yongbao Ma2Hongqing Liu3School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaSchool of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaSuresense Technology, Chongqing 400065, ChinaSchool of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, ChinaThe quality and intelligibility of the speech are usually impaired by the interference of background noise when using internet voice calls. To solve this problem in the context of wearable smart devices, this paper introduces a dual-microphone, bone-conduction (BC) sensor assisted beamformer and a simple recurrent unit (SRU)-based neural network postfilter for real-time speech enhancement. Assisted by the BC sensor, which is insensitive to the environmental noise compared to the regular air-conduction (AC) microphone, the accurate voice activity detection (VAD) can be obtained from the BC signal and incorporated into the adaptive noise canceller (ANC) and adaptive block matrix (ABM). The SRU-based postfilter consists of a recurrent neural network with a small number of parameters, which improves the computational efficiency. The sub-band signal processing is designed to compress the input features of the neural network, and the scale-invariant signal-to-distortion ratio (SI-SDR) is developed as the loss function to minimize the distortion of the desired speech signal. Experimental results demonstrate that the proposed real-time speech enhancement system provides significant speech sound quality and intelligibility improvements for all noise types and levels when compared with the AC-only beamformer with a postfiltering algorithm.https://www.mdpi.com/1424-8220/20/18/5050array signal processingbone conductionbeamformingspeech enhancementdeep learningreal time |
spellingShingle | Yi Zhou Yufan Chen Yongbao Ma Hongqing Liu A Real-Time Dual-Microphone Speech Enhancement Algorithm Assisted by Bone Conduction Sensor Sensors array signal processing bone conduction beamforming speech enhancement deep learning real time |
title | A Real-Time Dual-Microphone Speech Enhancement Algorithm Assisted by Bone Conduction Sensor |
title_full | A Real-Time Dual-Microphone Speech Enhancement Algorithm Assisted by Bone Conduction Sensor |
title_fullStr | A Real-Time Dual-Microphone Speech Enhancement Algorithm Assisted by Bone Conduction Sensor |
title_full_unstemmed | A Real-Time Dual-Microphone Speech Enhancement Algorithm Assisted by Bone Conduction Sensor |
title_short | A Real-Time Dual-Microphone Speech Enhancement Algorithm Assisted by Bone Conduction Sensor |
title_sort | real time dual microphone speech enhancement algorithm assisted by bone conduction sensor |
topic | array signal processing bone conduction beamforming speech enhancement deep learning real time |
url | https://www.mdpi.com/1424-8220/20/18/5050 |
work_keys_str_mv | AT yizhou arealtimedualmicrophonespeechenhancementalgorithmassistedbyboneconductionsensor AT yufanchen arealtimedualmicrophonespeechenhancementalgorithmassistedbyboneconductionsensor AT yongbaoma arealtimedualmicrophonespeechenhancementalgorithmassistedbyboneconductionsensor AT hongqingliu arealtimedualmicrophonespeechenhancementalgorithmassistedbyboneconductionsensor AT yizhou realtimedualmicrophonespeechenhancementalgorithmassistedbyboneconductionsensor AT yufanchen realtimedualmicrophonespeechenhancementalgorithmassistedbyboneconductionsensor AT yongbaoma realtimedualmicrophonespeechenhancementalgorithmassistedbyboneconductionsensor AT hongqingliu realtimedualmicrophonespeechenhancementalgorithmassistedbyboneconductionsensor |