Model-based Speech Enhancement for Intelligibility Improvement in Binaural Hearing Aids

Research output: Contribution to journalJournal articleResearchpeer-review

1 Citation (Scopus)
46 Downloads (Pure)

Abstract

Speech intelligibility is often severely degraded among hearing impaired individuals in situations such as the cocktail party scenario. The performance of the current hearing aid technology has been observed to be limited in these scenarios. In this paper, we propose a binaural speech enhancement framework that takes into consideration the speech production model. The enhancement framework proposed here is based on the Kalman filter that allows us to take the speech production dynamics into account during the enhancement process. The usage of a Kalman filter requires the estimation of clean speech and noise short term predictor (STP) parameters, and the clean speech pitch parameters. In this work, a binaural codebook-based method is proposed for estimating the STP parameters, and a directional pitch estimator based on the harmonic model and maximum likelihood principle is used to estimate the pitch parameters. The proposed method for estimating the STP and pitch parameters jointly uses the information from left and right ears, leading to a more robust estimation of the filter parameters. Objective measures such as PESQ and STOI have been used to evaluate the enhancement framework in different acoustic scenarios representative of the cocktail party scenario. We have also conducted subjective listening tests on a set of nine normal hearing subjects, to evaluate the performance in terms of intelligibility and quality improvement. The listening tests show that the proposed algorithm, even with access to only a single channel noisy observation, significantly improves the overall speech quality, and the speech intelligibility by up to 15%.
Original languageEnglish
JournalIEEE/ACM Transactions on Audio, Speech, and Language Processing
Volume27
Issue number1
Pages (from-to)99-113
ISSN2329-9290
DOIs
Publication statusPublished - Jan 2019

Fingerprint

binaural hearing
Speech intelligibility
Hearing aids
Speech enhancement
intelligibility
augmentation
Audition
hearing
Kalman filters
estimating
predictions
Maximum likelihood
Acoustics
ear
estimators
harmonics
filters

Cite this

@article{c241c8e3266f435f8b39f95fa0952679,
title = "Model-based Speech Enhancement for Intelligibility Improvement in Binaural Hearing Aids",
abstract = "Speech intelligibility is often severely degraded among hearing impaired individuals in situations such as the cocktail party scenario. The performance of the current hearing aid technology has been observed to be limited in these scenarios. In this paper, we propose a binaural speech enhancement framework that takes into consideration the speech production model. The enhancement framework proposed here is based on the Kalman filter that allows us to take the speech production dynamics into account during the enhancement process. The usage of a Kalman filter requires the estimation of clean speech and noise short term predictor (STP) parameters, and the clean speech pitch parameters. In this work, a binaural codebook-based method is proposed for estimating the STP parameters, and a directional pitch estimator based on the harmonic model and maximum likelihood principle is used to estimate the pitch parameters. The proposed method for estimating the STP and pitch parameters jointly uses the information from left and right ears, leading to a more robust estimation of the filter parameters. Objective measures such as PESQ and STOI have been used to evaluate the enhancement framework in different acoustic scenarios representative of the cocktail party scenario. We have also conducted subjective listening tests on a set of nine normal hearing subjects, to evaluate the performance in terms of intelligibility and quality improvement. The listening tests show that the proposed algorithm, even with access to only a single channel noisy observation, significantly improves the overall speech quality, and the speech intelligibility by up to 15{\%}.",
author = "Kavalekalam, {Mathew Shaji} and Nielsen, {Jesper Kj{\ae}r} and Boldt, {Jesper B{\"u}nsow} and Christensen, {Mads Gr{\ae}sb{\o}ll}",
year = "2019",
month = "1",
doi = "10.1109/TASLP.2018.2872128",
language = "English",
volume = "27",
pages = "99--113",
journal = "IEEE/ACM Transactions on Audio, Speech, and Language Processing",
issn = "2329-9290",
publisher = "IEEE Signal Processing Society",
number = "1",

}

Model-based Speech Enhancement for Intelligibility Improvement in Binaural Hearing Aids. / Kavalekalam, Mathew Shaji; Nielsen, Jesper Kjær; Boldt, Jesper Bünsow; Christensen, Mads Græsbøll.

In: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 27, No. 1, 01.2019, p. 99-113.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Model-based Speech Enhancement for Intelligibility Improvement in Binaural Hearing Aids

AU - Kavalekalam, Mathew Shaji

AU - Nielsen, Jesper Kjær

AU - Boldt, Jesper Bünsow

AU - Christensen, Mads Græsbøll

PY - 2019/1

Y1 - 2019/1

N2 - Speech intelligibility is often severely degraded among hearing impaired individuals in situations such as the cocktail party scenario. The performance of the current hearing aid technology has been observed to be limited in these scenarios. In this paper, we propose a binaural speech enhancement framework that takes into consideration the speech production model. The enhancement framework proposed here is based on the Kalman filter that allows us to take the speech production dynamics into account during the enhancement process. The usage of a Kalman filter requires the estimation of clean speech and noise short term predictor (STP) parameters, and the clean speech pitch parameters. In this work, a binaural codebook-based method is proposed for estimating the STP parameters, and a directional pitch estimator based on the harmonic model and maximum likelihood principle is used to estimate the pitch parameters. The proposed method for estimating the STP and pitch parameters jointly uses the information from left and right ears, leading to a more robust estimation of the filter parameters. Objective measures such as PESQ and STOI have been used to evaluate the enhancement framework in different acoustic scenarios representative of the cocktail party scenario. We have also conducted subjective listening tests on a set of nine normal hearing subjects, to evaluate the performance in terms of intelligibility and quality improvement. The listening tests show that the proposed algorithm, even with access to only a single channel noisy observation, significantly improves the overall speech quality, and the speech intelligibility by up to 15%.

AB - Speech intelligibility is often severely degraded among hearing impaired individuals in situations such as the cocktail party scenario. The performance of the current hearing aid technology has been observed to be limited in these scenarios. In this paper, we propose a binaural speech enhancement framework that takes into consideration the speech production model. The enhancement framework proposed here is based on the Kalman filter that allows us to take the speech production dynamics into account during the enhancement process. The usage of a Kalman filter requires the estimation of clean speech and noise short term predictor (STP) parameters, and the clean speech pitch parameters. In this work, a binaural codebook-based method is proposed for estimating the STP parameters, and a directional pitch estimator based on the harmonic model and maximum likelihood principle is used to estimate the pitch parameters. The proposed method for estimating the STP and pitch parameters jointly uses the information from left and right ears, leading to a more robust estimation of the filter parameters. Objective measures such as PESQ and STOI have been used to evaluate the enhancement framework in different acoustic scenarios representative of the cocktail party scenario. We have also conducted subjective listening tests on a set of nine normal hearing subjects, to evaluate the performance in terms of intelligibility and quality improvement. The listening tests show that the proposed algorithm, even with access to only a single channel noisy observation, significantly improves the overall speech quality, and the speech intelligibility by up to 15%.

U2 - 10.1109/TASLP.2018.2872128

DO - 10.1109/TASLP.2018.2872128

M3 - Journal article

VL - 27

SP - 99

EP - 113

JO - IEEE/ACM Transactions on Audio, Speech, and Language Processing

JF - IEEE/ACM Transactions on Audio, Speech, and Language Processing

SN - 2329-9290

IS - 1

ER -