DFT-Domain Based Single-Microphone Noise Reduction for Speech Enhancement: A Survey of the State of the Art

Richard C. Hendriks, Timo Gerkmann, Jesper Jensen

Publikation: Bog/antologi/afhandling/rapportBogForskningpeer review

39 Citationer (Scopus)

Resumé

As speech processing devices like mobile phones, voice controlled devices, and hearing aids have increased in popularity, people expect them to work anywhere and at any time without user intervention. However, the presence of acoustical disturbances limits the use of these applications, degrades their performance, or causes the user difficulties in understanding the conversation or appreciating the device. A common way to reduce the effects of such disturbances is through the use of single-microphone noise reduction algorithms for speech enhancement.

The field of single-microphone noise reduction for speech enhancement comprises a history of more than 30 years of research. In this survey, we wish to demonstrate the significant advances that have been made during the last decade in the field of discrete Fourier transform domain-based single-channel noise reduction for speech enhancement.Furthermore, our goal is to provide a concise description of a state-of-the-art speech enhancement system, and demonstrate the relative importance of the various building blocks of such a system. This allows the non-expert DSP practitioner to judge the relevance of each building block and to implement a close-to-optimal enhancement system for the particular application at hand.

Table of Contents: Introduction / Single Channel Speech Enhancement: General Principles / DFT-Based Speech Enhancement Methods: Signal Model and Notation / Speech DFT Estimators / Speech Presence Probability Estimation / Noise PSD Estimation / Speech PSD Estimation / Performance Evaluation Methods / Simulation Experiments with Single-Channel Enhancement Systems / Future Directions
OriginalsprogEngelsk
ForlagMorgan & Claypool Publishers
Antal sider80
ISBN (Trykt)9781627051439
ISBN (Elektronisk)9781627051446
DOI
StatusUdgivet - 2013
NavnSynthesis Lectures on Speech and Audio Processing
Nummer11
ISSN1932-121X

Fingerprint

Speech enhancement
Microphones
Noise abatement
Discrete Fourier transforms
Hearing aids
Speech processing
Mobile phones

Citer dette

C. Hendriks, R., Gerkmann, T., & Jensen, J. (2013). DFT-Domain Based Single-Microphone Noise Reduction for Speech Enhancement: A Survey of the State of the Art. Morgan & Claypool Publishers. Synthesis Lectures on Speech and Audio Processing, Nr. 11 https://doi.org/10.2200/S00473ED1V01Y201301SAP011
C. Hendriks, Richard ; Gerkmann, Timo ; Jensen, Jesper. / DFT-Domain Based Single-Microphone Noise Reduction for Speech Enhancement : A Survey of the State of the Art. Morgan & Claypool Publishers, 2013. 80 s. (Synthesis Lectures on Speech and Audio Processing; Nr. 11).
@book{413705d5180c4f5ea2eb7b60abfe4cfc,
title = "DFT-Domain Based Single-Microphone Noise Reduction for Speech Enhancement: A Survey of the State of the Art",
abstract = "As speech processing devices like mobile phones, voice controlled devices, and hearing aids have increased in popularity, people expect them to work anywhere and at any time without user intervention. However, the presence of acoustical disturbances limits the use of these applications, degrades their performance, or causes the user difficulties in understanding the conversation or appreciating the device. A common way to reduce the effects of such disturbances is through the use of single-microphone noise reduction algorithms for speech enhancement. The field of single-microphone noise reduction for speech enhancement comprises a history of more than 30 years of research. In this survey, we wish to demonstrate the significant advances that have been made during the last decade in the field of discrete Fourier transform domain-based single-channel noise reduction for speech enhancement.Furthermore, our goal is to provide a concise description of a state-of-the-art speech enhancement system, and demonstrate the relative importance of the various building blocks of such a system. This allows the non-expert DSP practitioner to judge the relevance of each building block and to implement a close-to-optimal enhancement system for the particular application at hand.",
author = "{C. Hendriks}, Richard and Timo Gerkmann and Jesper Jensen",
year = "2013",
doi = "10.2200/S00473ED1V01Y201301SAP011",
language = "English",
isbn = "9781627051439",
series = "Synthesis Lectures on Speech and Audio Processing",
publisher = "Morgan & Claypool Publishers",
number = "11",

}

C. Hendriks, R, Gerkmann, T & Jensen, J 2013, DFT-Domain Based Single-Microphone Noise Reduction for Speech Enhancement: A Survey of the State of the Art. Synthesis Lectures on Speech and Audio Processing, nr. 11, Morgan & Claypool Publishers. https://doi.org/10.2200/S00473ED1V01Y201301SAP011

DFT-Domain Based Single-Microphone Noise Reduction for Speech Enhancement : A Survey of the State of the Art. / C. Hendriks, Richard ; Gerkmann, Timo ; Jensen, Jesper.

Morgan & Claypool Publishers, 2013. 80 s. (Synthesis Lectures on Speech and Audio Processing; Nr. 11).

Publikation: Bog/antologi/afhandling/rapportBogForskningpeer review

TY - BOOK

T1 - DFT-Domain Based Single-Microphone Noise Reduction for Speech Enhancement

T2 - A Survey of the State of the Art

AU - C. Hendriks, Richard

AU - Gerkmann, Timo

AU - Jensen, Jesper

PY - 2013

Y1 - 2013

N2 - As speech processing devices like mobile phones, voice controlled devices, and hearing aids have increased in popularity, people expect them to work anywhere and at any time without user intervention. However, the presence of acoustical disturbances limits the use of these applications, degrades their performance, or causes the user difficulties in understanding the conversation or appreciating the device. A common way to reduce the effects of such disturbances is through the use of single-microphone noise reduction algorithms for speech enhancement. The field of single-microphone noise reduction for speech enhancement comprises a history of more than 30 years of research. In this survey, we wish to demonstrate the significant advances that have been made during the last decade in the field of discrete Fourier transform domain-based single-channel noise reduction for speech enhancement.Furthermore, our goal is to provide a concise description of a state-of-the-art speech enhancement system, and demonstrate the relative importance of the various building blocks of such a system. This allows the non-expert DSP practitioner to judge the relevance of each building block and to implement a close-to-optimal enhancement system for the particular application at hand.

AB - As speech processing devices like mobile phones, voice controlled devices, and hearing aids have increased in popularity, people expect them to work anywhere and at any time without user intervention. However, the presence of acoustical disturbances limits the use of these applications, degrades their performance, or causes the user difficulties in understanding the conversation or appreciating the device. A common way to reduce the effects of such disturbances is through the use of single-microphone noise reduction algorithms for speech enhancement. The field of single-microphone noise reduction for speech enhancement comprises a history of more than 30 years of research. In this survey, we wish to demonstrate the significant advances that have been made during the last decade in the field of discrete Fourier transform domain-based single-channel noise reduction for speech enhancement.Furthermore, our goal is to provide a concise description of a state-of-the-art speech enhancement system, and demonstrate the relative importance of the various building blocks of such a system. This allows the non-expert DSP practitioner to judge the relevance of each building block and to implement a close-to-optimal enhancement system for the particular application at hand.

U2 - 10.2200/S00473ED1V01Y201301SAP011

DO - 10.2200/S00473ED1V01Y201301SAP011

M3 - Book

SN - 9781627051439

T3 - Synthesis Lectures on Speech and Audio Processing

BT - DFT-Domain Based Single-Microphone Noise Reduction for Speech Enhancement

PB - Morgan & Claypool Publishers

ER -

C. Hendriks R, Gerkmann T, Jensen J. DFT-Domain Based Single-Microphone Noise Reduction for Speech Enhancement: A Survey of the State of the Art. Morgan & Claypool Publishers, 2013. 80 s. (Synthesis Lectures on Speech and Audio Processing; Nr. 11). https://doi.org/10.2200/S00473ED1V01Y201301SAP011