EEG-Informed Attended Speaker Extraction From Recorded Speech Mixtures With Application in Neuro-Steered Hearing Prostheses

Eyndhoven, Simon Van; Francart, Tom; Bertrand, Alexander

doi:10.1109/tbme.2016.2587382

Cited by 122 publications

(145 citation statements)

References 25 publications

(69 reference statements)

Supporting

Mentioning

145

Contrasting

Order By: Relevance

“…For example, to design so-called neuro-steered hearing prostheses [5], [6], a small EEG module can be integrated into a hearing prosthesis for in-the-ear [7] or around-theear [8] EEG recordings, and even the implanted electrodes of a cochlear implant can be used to record EEG [9]. Such small EEG modules are discreet, albeit limited in number of channels and spatial coverage.…”

Section: Introductionmentioning

confidence: 99%

Removal of eye blink artifacts in wireless EEG sensor networks using reduced-bandwidth canonical correlation analysis

Somers

Bertrand

2016

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

Removal of eye blink artifacts in wireless EEG sensor networks using reduced-bandwidth canonical correlation analysisJournal of Neural Engineering, vol. 13, no. 6, pp. 066008, 2016. Archived versionAuthor manuscript: the content is identical to the content of the published paper, but without the final typesetting by the publisher Abstract-Objective: Chronic, 24/7 EEG monitoring requires the use of highly miniaturized EEG modules, which only measure a few EEG channels over a small area. For improved spatial coverage, a wireless EEG sensor network (WESN) can be deployed, consisting of multiple EEG modules, which interact through short-distance wireless communication. In this paper, we aim to remove eye blink artifacts in each EEG channel of a WESN by optimally exploiting the correlation between EEG signals from different modules, under stringent communication bandwidth constraints. Approach: We apply a distributed canonical correlation analysis (CCA-)based algorithm, in which each module only transmits an optimal linear combination of its local EEG channels to the other modules. The method is validated on both synthetic and real EEG data sets, with emulated wireless transmissions. Main Results: While strongly reducing the amount of data that is shared between nodes, we demonstrate that the algorithm achieves the same eye blink artifact removal performance as the equivalent centralized CCA algorithm, which is at least as good as other state-of-the-art multi-channel algorithms that require a transmission of all channels. Significance: Due to their potential for extreme miniaturization, WESNs are viewed as an enabling technology for chronic EEG monitoring. However, multi-channel analysis is hampered in WESNs due to the high energy cost for wireless communication. This paper shows that multi-channel eye blink artifact removal is possible with a significantly reduced wireless communication between EEG modules.

show abstract

Section: Introductionmentioning

confidence: 99%

Removal of eye blink artifacts in wireless EEG sensor networks using reduced-bandwidth canonical correlation analysis

Somers

Bertrand

2016

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…We aim to enhance the speech component of one speaker, while suppressing that of the other speakers and noise. As described in [3], [12], this can be achieved using a multi-channel Wiener filter (MWF) w(ω), that extracts the attended speech streams att (ω) = w(ω) H y(ω) provided that we have the knowledge of the times at which the attended speaker is active (superscript H denotes the conjugate transpose operator).…”

Section: A Data Model and Problem Statementmentioning

confidence: 99%

“…However, in a multi-speaker scenario, a fundamental challenge is to determine which speaker the listener actually aims to focus on. Therefore, incorporating a brain-computer interface to infer the auditory attention of the listener opens up an interesting field of research aiming to build smarter hearing prostheses [3].…”

Section: Introductionmentioning

confidence: 99%

“…suppression systems in hearing aids to form neuro-steered hearing prostheses. A proof of concept for this idea was presented in [3] where a pre-trained AAD decoder reconstructed the attended speech stream's envelope from EEG recordings, which was then correlated with speech envelopes extracted from microphone signals using a blind envelope demixing algorithm. The envelope with the higher correlation with the reconstructed attended speech stream was considered to belong to the attended speaker.…”

Section: Introductionmentioning

confidence: 99%

“…We propose an improved algorithm where multiple MWFs receive different speaker-dependent voice activity information from the speaker envelopes extracted by the blind envelope demixing algorithm (unlike in [3] where a single MWF received the speaker voice activity track chosen by the AAD module). Also, instead of using the envelopes extracted from the demixing algorithm directly for attention detection, we use envelopes extracted from the output of the multiple MWFs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

EEG-based attention-driven speech enhancement for noisy speech mixtures using N-fold multi-channel Wiener filters

Das

Eyndhoven

Francart

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

Abstract-Hearing prostheses have built-in algorithms to perform acoustic noise reduction and improve speech intelligibility. However, in a multi-speaker scenario the noise reduction algorithm has to determine which speaker the listener is focusing on, in order to enhance it while suppressing the other interfering sources. Recently, it has been demonstrated that it is possible to detect auditory attention using electroencephalography (EEG). In this paper, we use multi-channel Wiener filters (MWFs), to filter out each speech stream from the speech mixtures in the microphones of a binaural hearing aid, while also reducing background noise. From the demixed and denoised speech streams, we extract envelopes for an EEG-based auditory attention detection (AAD) algorithm. The AAD module can then select the output of the MWF corresponding to the attended speaker. We evaluate our algorithm in a two-speaker scenario in the presence of babble noise and compare it to a previously proposed algorithm. Our algorithm is observed to provide speech envelopes that yield better AAD accuracies, and is more robust to variations in speaker positions and diffuse background noise.

show abstract

Recent advances and current trends in brain‐computer interface research and their applications

Žabčíková

Koudelková

Jašek

et al. 2022

Intl J of Devlp Neuroscience

View full text Add to dashboard Cite

Brain‐computer interface (BCI) provides direct communication between the brain and an external device. BCI systems have become a trendy field of research in recent years. These systems can be used in a variety of applications to help both disabled and healthy people. Concerning significant BCI progress, we may assume that these systems are not very far from real‐world applications. This review has taken into account current trends in BCI research. In this survey, 100 most cited articles from the WOS database were selected over the last 4 years. This survey is divided into several sectors. These sectors are Medicine, Communication and Control, Entertainment, and Other BCI applications. The application area, recording method, signal acquisition types, and countries of origin have been identified in each article. This survey provides an overview of the BCI articles published from 2016 to 2020 and their current trends and advances in different application areas.

show abstract

EEG-Informed Attended Speaker Extraction From Recorded Speech Mixtures With Application in Neuro-Steered Hearing Prostheses

Cited by 122 publications

References 25 publications

Removal of eye blink artifacts in wireless EEG sensor networks using reduced-bandwidth canonical correlation analysis

Removal of eye blink artifacts in wireless EEG sensor networks using reduced-bandwidth canonical correlation analysis

EEG-based attention-driven speech enhancement for noisy speech mixtures using N-fold multi-channel Wiener filters

Recent advances and current trends in brain‐computer interface research and their applications

Contact Info

Product

Resources

About