Voice activity detection from electrocorticographic signals

Vasileios G. Kanas, I. Mporas, H. L. Benz, N. Huang, Nitish V Thakor, K. Sgarbas, A. Bezerianos, Nathan E Crone

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

The purpose of this study was to explore voice activity detection (VAD) in a subject with implanted electrocorticographic (ECoG) electrodes. Accurate VAD is an important preliminary step before decoding and reconstructing speech from ECoG. For this study we used ECoG signals recorded while a subject performed a picture naming task. We extracted time-domain features from the raw ECoG and spectral features from the ECoG high gamma band (70-110Hz). The RelieF algorithm was used for selecting a subset of features to use with seven machine learning algorithms for classification. With this approach we were able to detect voice activity from ECoG signals, achieving a high accuracy using the 100 best features from all electrodes (96%) or only 12 features from the two best electrodes (94%) using the support vector machines or a linear regression classifier. These findings may contribute to the development of ECoG-based brain machine interface (BMI) systems for rehabilitating individuals with communication impairments.

Original languageEnglish (US)
Title of host publicationIFMBE Proceedings
Pages1643-1646
Number of pages4
Volume41
DOIs
StatePublished - 2014
Event13th Mediterranean Conference on Medical and Biological Engineering and Computing 2013, MEDICON 2013 - Seville, Spain
Duration: Sep 25 2013Sep 28 2013

Other

Other13th Mediterranean Conference on Medical and Biological Engineering and Computing 2013, MEDICON 2013
CountrySpain
CitySeville
Period9/25/139/28/13

Fingerprint

Electrodes
Set theory
Linear regression
Learning algorithms
Support vector machines
Decoding
Learning systems
Brain
Classifiers
Communication

Keywords

  • Brain machine interface
  • Electrocorticography
  • Machine learning
  • Voice activity detection

ASJC Scopus subject areas

  • Biomedical Engineering
  • Bioengineering

Cite this

Kanas, V. G., Mporas, I., Benz, H. L., Huang, N., Thakor, N. V., Sgarbas, K., ... Crone, N. E. (2014). Voice activity detection from electrocorticographic signals. In IFMBE Proceedings (Vol. 41, pp. 1643-1646) https://doi.org/10.1007/978-3-319-00846-2_405

Voice activity detection from electrocorticographic signals. / Kanas, Vasileios G.; Mporas, I.; Benz, H. L.; Huang, N.; Thakor, Nitish V; Sgarbas, K.; Bezerianos, A.; Crone, Nathan E.

IFMBE Proceedings. Vol. 41 2014. p. 1643-1646.

Research output: Chapter in Book/Report/Conference proceedingChapter

Kanas, VG, Mporas, I, Benz, HL, Huang, N, Thakor, NV, Sgarbas, K, Bezerianos, A & Crone, NE 2014, Voice activity detection from electrocorticographic signals. in IFMBE Proceedings. vol. 41, pp. 1643-1646, 13th Mediterranean Conference on Medical and Biological Engineering and Computing 2013, MEDICON 2013, Seville, Spain, 9/25/13. https://doi.org/10.1007/978-3-319-00846-2_405
Kanas VG, Mporas I, Benz HL, Huang N, Thakor NV, Sgarbas K et al. Voice activity detection from electrocorticographic signals. In IFMBE Proceedings. Vol. 41. 2014. p. 1643-1646 https://doi.org/10.1007/978-3-319-00846-2_405
Kanas, Vasileios G. ; Mporas, I. ; Benz, H. L. ; Huang, N. ; Thakor, Nitish V ; Sgarbas, K. ; Bezerianos, A. ; Crone, Nathan E. / Voice activity detection from electrocorticographic signals. IFMBE Proceedings. Vol. 41 2014. pp. 1643-1646
@inbook{cdceb1bd33914925bcbd426670a75cc8,
title = "Voice activity detection from electrocorticographic signals",
abstract = "The purpose of this study was to explore voice activity detection (VAD) in a subject with implanted electrocorticographic (ECoG) electrodes. Accurate VAD is an important preliminary step before decoding and reconstructing speech from ECoG. For this study we used ECoG signals recorded while a subject performed a picture naming task. We extracted time-domain features from the raw ECoG and spectral features from the ECoG high gamma band (70-110Hz). The RelieF algorithm was used for selecting a subset of features to use with seven machine learning algorithms for classification. With this approach we were able to detect voice activity from ECoG signals, achieving a high accuracy using the 100 best features from all electrodes (96{\%}) or only 12 features from the two best electrodes (94{\%}) using the support vector machines or a linear regression classifier. These findings may contribute to the development of ECoG-based brain machine interface (BMI) systems for rehabilitating individuals with communication impairments.",
keywords = "Brain machine interface, Electrocorticography, Machine learning, Voice activity detection",
author = "Kanas, {Vasileios G.} and I. Mporas and Benz, {H. L.} and N. Huang and Thakor, {Nitish V} and K. Sgarbas and A. Bezerianos and Crone, {Nathan E}",
year = "2014",
doi = "10.1007/978-3-319-00846-2_405",
language = "English (US)",
isbn = "9783319008455",
volume = "41",
pages = "1643--1646",
booktitle = "IFMBE Proceedings",

}

TY - CHAP

T1 - Voice activity detection from electrocorticographic signals

AU - Kanas, Vasileios G.

AU - Mporas, I.

AU - Benz, H. L.

AU - Huang, N.

AU - Thakor, Nitish V

AU - Sgarbas, K.

AU - Bezerianos, A.

AU - Crone, Nathan E

PY - 2014

Y1 - 2014

N2 - The purpose of this study was to explore voice activity detection (VAD) in a subject with implanted electrocorticographic (ECoG) electrodes. Accurate VAD is an important preliminary step before decoding and reconstructing speech from ECoG. For this study we used ECoG signals recorded while a subject performed a picture naming task. We extracted time-domain features from the raw ECoG and spectral features from the ECoG high gamma band (70-110Hz). The RelieF algorithm was used for selecting a subset of features to use with seven machine learning algorithms for classification. With this approach we were able to detect voice activity from ECoG signals, achieving a high accuracy using the 100 best features from all electrodes (96%) or only 12 features from the two best electrodes (94%) using the support vector machines or a linear regression classifier. These findings may contribute to the development of ECoG-based brain machine interface (BMI) systems for rehabilitating individuals with communication impairments.

AB - The purpose of this study was to explore voice activity detection (VAD) in a subject with implanted electrocorticographic (ECoG) electrodes. Accurate VAD is an important preliminary step before decoding and reconstructing speech from ECoG. For this study we used ECoG signals recorded while a subject performed a picture naming task. We extracted time-domain features from the raw ECoG and spectral features from the ECoG high gamma band (70-110Hz). The RelieF algorithm was used for selecting a subset of features to use with seven machine learning algorithms for classification. With this approach we were able to detect voice activity from ECoG signals, achieving a high accuracy using the 100 best features from all electrodes (96%) or only 12 features from the two best electrodes (94%) using the support vector machines or a linear regression classifier. These findings may contribute to the development of ECoG-based brain machine interface (BMI) systems for rehabilitating individuals with communication impairments.

KW - Brain machine interface

KW - Electrocorticography

KW - Machine learning

KW - Voice activity detection

UR - http://www.scopus.com/inward/record.url?scp=84891286469&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891286469&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-00846-2_405

DO - 10.1007/978-3-319-00846-2_405

M3 - Chapter

AN - SCOPUS:84891286469

SN - 9783319008455

VL - 41

SP - 1643

EP - 1646

BT - IFMBE Proceedings

ER -