Header

UZH-Logo

Maintenance Infos

Brain-informed speech separation (BISS) for enhancement of target speaker in multitalker speech perception


Ceolini, Enea; Hjortkjær, Jens; Wong, Daniel DE; O’Sullivan, James; Raghavan, Vinay S; Herrero, Jose; Mehta, Ashesh D; Liu, Shih-Chii; Mesgarani, Nima (2020). Brain-informed speech separation (BISS) for enhancement of target speaker in multitalker speech perception. NeuroImage, 223:117282.

Abstract

Hearing-impaired people often struggle to follow the speech stream of an individual talker in noisy environments. Recent studies show that the brain tracks attended speech and that the attended talker can be decoded from neural data on a single-trial level. This raises the possibility of “neuro-steered” hearing devices in which the brain-decoded intention of a hearing-impaired listener is used to enhance the voice of the attended speaker from a speech separation front-end. So far, methods that use this paradigm have focused on optimizing the brain decoding and the acoustic speech separation independently. In this work, we propose a novel framework called brain-informed speech separation (BISS)1 in which the information about the attended speech, as decoded from the subject’s brain, is directly used to perform speech separation in the front-end. We present a deep learning model that uses neural data to extract the clean audio signal that a listener is attending to from a multi-talker speech mixture. We show that the framework can be applied successfully to the decoded output from either invasive intracranial electroencephalography (iEEG) or non-invasive electroencephalography (EEG) recordings from hearing-impaired subjects. It also results in improved speech separation, even in scenes with background noise. The generalization capability of the system renders it a perfect candidate for neuro-steered hearing-assistive devices.

Abstract

Hearing-impaired people often struggle to follow the speech stream of an individual talker in noisy environments. Recent studies show that the brain tracks attended speech and that the attended talker can be decoded from neural data on a single-trial level. This raises the possibility of “neuro-steered” hearing devices in which the brain-decoded intention of a hearing-impaired listener is used to enhance the voice of the attended speaker from a speech separation front-end. So far, methods that use this paradigm have focused on optimizing the brain decoding and the acoustic speech separation independently. In this work, we propose a novel framework called brain-informed speech separation (BISS)1 in which the information about the attended speech, as decoded from the subject’s brain, is directly used to perform speech separation in the front-end. We present a deep learning model that uses neural data to extract the clean audio signal that a listener is attending to from a multi-talker speech mixture. We show that the framework can be applied successfully to the decoded output from either invasive intracranial electroencephalography (iEEG) or non-invasive electroencephalography (EEG) recordings from hearing-impaired subjects. It also results in improved speech separation, even in scenes with background noise. The generalization capability of the system renders it a perfect candidate for neuro-steered hearing-assistive devices.

Statistics

Citations

Altmetrics

Downloads

0 downloads since deposited on 15 Feb 2021
0 downloads since 12 months

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Scopus Subject Areas:Life Sciences > Neurology
Life Sciences > Cognitive Neuroscience
Uncontrolled Keywords:Cognitive Neuroscience, Neurology
Language:English
Date:1 December 2020
Deposited On:15 Feb 2021 12:39
Last Modified:16 Feb 2021 21:01
Publisher:Elsevier
ISSN:1053-8119
OA Status:Gold
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1016/j.neuroimage.2020.117282

Download

Gold Open Access

Download PDF  'Brain-informed speech separation (BISS) for enhancement of target speaker in multitalker speech perception'.
Preview
Content: Published Version
Filetype: PDF
Size: 3MB
View at publisher
Licence: Creative Commons: Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)