Model based Binaural Enhancement of Voiced and Unvoiced Speech

Mathew Shaji Kavalekalam; Mads Græsbøll Christensen; Jesper B. Boldt

doi:10.1109/ICASSP.2017.7952239

Model based Binaural Enhancement of Voiced and Unvoiced Speech

Mathew Shaji Kavalekalam, Mads Græsbøll Christensen, Jesper B. Boldt

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

5 Citations (Scopus)

450 Downloads (Pure)

Abstract

This paper deals with the enhancement of speech in presence
of non-stationary babble noise. A binaural speech enhancement framework is proposed which takes into account both
the voiced and unvoiced speech production model. The usage
of this model in enhancement requires the Short term predictor (STP) parameters and the pitch information to be estimated. This paper uses a codebook based approach for estimating the STP parameters and a parametric binaural method
is proposed for estimating the pitch parameters. Improvements in objective score are shown when using the voicedunvoiced speech model in comparison to the conventional unvoiced speech model

Original language	English
Title of host publication	IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017
Publisher	IEEE
Publication date	2017
Pages	666-670
ISBN (Electronic)	978-1-5090-4117-6
DOIs	https://doi.org/10.1109/ICASSP.2017.7952239
Publication status	Published - 2017
Event	The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing: The Internet of Signals - New Orleans, United States Duration: 5 Mar 2017 → 9 Mar 2017 http://www.ieee-icassp2017.org/ http://www.ieee-icassp2017.org/

Conference

Conference	The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing
Country/Territory	United States
City	New Orleans
Period	05/03/2017 → 09/03/2017
Internet address	http://www.ieee-icassp2017.org/ http://www.ieee-icassp2017.org/

Series	I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
ISSN	1520-6149

Access to Document

10.1109/ICASSP.2017.7952239

kavalekalamAccepted author manuscript, 857 KB

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{d1a09609837747c9998352997a2a747c,

title = "Model based Binaural Enhancement of Voiced and Unvoiced Speech",

abstract = "This paper deals with the enhancement of speech in presenceof non-stationary babble noise. A binaural speech enhancement framework is proposed which takes into account boththe voiced and unvoiced speech production model. The usageof this model in enhancement requires the Short term predictor (STP) parameters and the pitch information to be estimated. This paper uses a codebook based approach for estimating the STP parameters and a parametric binaural methodis proposed for estimating the pitch parameters. Improvements in objective score are shown when using the voicedunvoiced speech model in comparison to the conventional unvoiced speech model",

author = "Kavalekalam, {Mathew Shaji} and Christensen, {Mads Gr{\ae}sb{\o}ll} and Boldt, {Jesper B.}",

year = "2017",

doi = "10.1109/ICASSP.2017.7952239",

language = "English",

series = "I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings",

publisher = "IEEE",

pages = "666--670",

booktitle = "IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017",

address = "United States",

note = "The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing : The Internet of Signals, ICASSP2017 ; Conference date: 05-03-2017 Through 09-03-2017",

url = "http://www.ieee-icassp2017.org/, http://www.ieee-icassp2017.org/",

}

Kavalekalam, MS, Christensen, MG & Boldt, JB 2017, Model based Binaural Enhancement of Voiced and Unvoiced Speech. in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017. IEEE, I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, pp. 666-670, The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, United States, 05/03/2017. https://doi.org/10.1109/ICASSP.2017.7952239

Model based Binaural Enhancement of Voiced and Unvoiced Speech. / Kavalekalam, Mathew Shaji; Christensen, Mads Græsbøll; Boldt, Jesper B.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017. IEEE, 2017. p. 666-670 (I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Model based Binaural Enhancement of Voiced and Unvoiced Speech

AU - Kavalekalam, Mathew Shaji

AU - Christensen, Mads Græsbøll

AU - Boldt, Jesper B.

PY - 2017

Y1 - 2017

N2 - This paper deals with the enhancement of speech in presenceof non-stationary babble noise. A binaural speech enhancement framework is proposed which takes into account boththe voiced and unvoiced speech production model. The usageof this model in enhancement requires the Short term predictor (STP) parameters and the pitch information to be estimated. This paper uses a codebook based approach for estimating the STP parameters and a parametric binaural methodis proposed for estimating the pitch parameters. Improvements in objective score are shown when using the voicedunvoiced speech model in comparison to the conventional unvoiced speech model

AB - This paper deals with the enhancement of speech in presenceof non-stationary babble noise. A binaural speech enhancement framework is proposed which takes into account boththe voiced and unvoiced speech production model. The usageof this model in enhancement requires the Short term predictor (STP) parameters and the pitch information to be estimated. This paper uses a codebook based approach for estimating the STP parameters and a parametric binaural methodis proposed for estimating the pitch parameters. Improvements in objective score are shown when using the voicedunvoiced speech model in comparison to the conventional unvoiced speech model

U2 - 10.1109/ICASSP.2017.7952239

DO - 10.1109/ICASSP.2017.7952239

M3 - Article in proceeding

T3 - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings

SP - 666

EP - 670

BT - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017

PB - IEEE

T2 - The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing

Y2 - 5 March 2017 through 9 March 2017

ER -

Model based Binaural Enhancement of Voiced and Unvoiced Speech

Abstract

Conference

Access to Document

AUB Link

Fingerprint

Cite this