Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Low-Latency Real-Time Blind Source Separation for Hearing Aids Based on Time-Domain Implementation of Online Independent Vector Analysis with Truncation of Non-Causal Components

Abstract: 

In this paper, we present a low-latency scheme for real-time blind source separation (BSS) based on online auxiliary-function-based independent vector analysis (AuxIVA). In many real-time audio ap- plications, especially hearing aids, low latency is highly desirable. Conventional frequency-domain BSS methods suffer from a delay caused by frame analysis. To reduce the delay, we implement sep- aration filters as multiple FIR filters in the time domain, which are converted from demixing matrices estimated by online AuxIVA in the frequency domain. Also, to further reduce the latency, part of the non-causal components of the FIR filters are truncated on the basis of causality analysis for ideal separation filters using a simple model. By experimental evaluation using a head and torso simulator in a real environment, the proposed algorithm with an algorithmic delay of less than 10 ms exhibited a separation performance of 7.7 dB in terms of the signal-to-interference ratio (SIR), which was less than 1.4 dB degradation from the case of conventional frequency-domain implementation.

up
0 users have voted:

Paper Details

Authors:
Masahiro Sunohara, Chiho Haruta, Nobutaka Ono
Submitted On:
6 March 2017 - 11:00am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Masahiro Sunohara
Paper Code:
AASP-L8.02
Document Year:
2017
Cite

Document Files

Low-latency real-time BSS for hearing aids

(138 downloads)

Subscribe

[1] Masahiro Sunohara, Chiho Haruta, Nobutaka Ono, "Low-Latency Real-Time Blind Source Separation for Hearing Aids Based on Time-Domain Implementation of Online Independent Vector Analysis with Truncation of Non-Causal Components", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1651. Accessed: Dec. 15, 2017.
@article{1651-17,
url = {http://sigport.org/1651},
author = {Masahiro Sunohara; Chiho Haruta; Nobutaka Ono },
publisher = {IEEE SigPort},
title = {Low-Latency Real-Time Blind Source Separation for Hearing Aids Based on Time-Domain Implementation of Online Independent Vector Analysis with Truncation of Non-Causal Components},
year = {2017} }
TY - EJOUR
T1 - Low-Latency Real-Time Blind Source Separation for Hearing Aids Based on Time-Domain Implementation of Online Independent Vector Analysis with Truncation of Non-Causal Components
AU - Masahiro Sunohara; Chiho Haruta; Nobutaka Ono
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1651
ER -
Masahiro Sunohara, Chiho Haruta, Nobutaka Ono. (2017). Low-Latency Real-Time Blind Source Separation for Hearing Aids Based on Time-Domain Implementation of Online Independent Vector Analysis with Truncation of Non-Causal Components. IEEE SigPort. http://sigport.org/1651
Masahiro Sunohara, Chiho Haruta, Nobutaka Ono, 2017. Low-Latency Real-Time Blind Source Separation for Hearing Aids Based on Time-Domain Implementation of Online Independent Vector Analysis with Truncation of Non-Causal Components. Available at: http://sigport.org/1651.
Masahiro Sunohara, Chiho Haruta, Nobutaka Ono. (2017). "Low-Latency Real-Time Blind Source Separation for Hearing Aids Based on Time-Domain Implementation of Online Independent Vector Analysis with Truncation of Non-Causal Components." Web.
1. Masahiro Sunohara, Chiho Haruta, Nobutaka Ono. Low-Latency Real-Time Blind Source Separation for Hearing Aids Based on Time-Domain Implementation of Online Independent Vector Analysis with Truncation of Non-Causal Components [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1651