Kalman filter for speech enhancement in cocktail party scenarios using a codebook-based approach

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

doi:10.1109/ICASSP.2016.7471663

Kalman filter for speech enhancement in cocktail party scenarios using a codebook-based approach

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

Department of Architecture, Design and Media Technology

Research output: Contribution to journal › Conference article in Journal › Research › peer-review

17 Citations (Scopus)

Abstract

Enhancement of speech in non-stationary background noise is a challenging task, and conventional single channel speech enhancement algorithms have not been able to improve the speech intelligibility in such scenarios. The work proposed in this paper investigates a single channel Kalman filter based speech enhancement algorithm, whose parameters are estimated using a codebook based approach. The results indicate that the enhancement algorithm is able to improve the speech intelligibility and quality according to objective measures. Moreover, we investigate the effects of utilizing a speaker specific trained codebook over a generic speech codebook in relation to the performance of the speech enhancement system.

Original language	English
Journal	I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
ISSN	1520-6149
DOIs	https://doi.org/10.1109/ICASSP.2016.7471663
Publication status	Published - Apr 2016
Event	The 41st IEEE International Conference on Acoustics, Speech and Signal Processing - Shanghai, China Duration: 20 Mar 2016 → 25 Mar 2016 http://www.icassp2016.org/

Conference

Conference	The 41st IEEE International Conference on Acoustics, Speech and Signal Processing
Country/Territory	China
City	Shanghai
Period	20/03/2016 → 25/03/2016
Internet address	http://www.icassp2016.org/

Access to Document

10.1109/ICASSP.2016.7471663

AUB Link

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

Cite this

@inproceedings{dfa20b1e2a9e44809efc0dd6d2f9cb90,

title = "Kalman filter for speech enhancement in cocktail party scenarios using a codebook-based approach",

abstract = "Enhancement of speech in non-stationary background noise is a challenging task, and conventional single channel speech enhancement algorithms have not been able to improve the speech intelligibility in such scenarios. The work proposed in this paper investigates a single channel Kalman filter based speech enhancement algorithm, whose parameters are estimated using a codebook based approach. The results indicate that the enhancement algorithm is able to improve the speech intelligibility and quality according to objective measures. Moreover, we investigate the effects of utilizing a speaker specific trained codebook over a generic speech codebook in relation to the performance of the speech enhancement system.",

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

year = "2016",

month = apr,

doi = "10.1109/ICASSP.2016.7471663",

language = "English",

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

issn = "1520-6149",

publisher = "IEEE Signal Processing Society",

note = "The 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 ; Conference date: 20-03-2016 Through 25-03-2016",

url = "http://www.icassp2016.org/",

}

Kalman filter for speech enhancement in cocktail party scenarios using a codebook-based approach. / Kavalekalam, Mathew Shaji; Christensen, Mads Græsbøll; Gran, Fredrik et al.
In: I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings, 04.2016.

Research output: Contribution to journal › Conference article in Journal › Research › peer-review

TY - GEN

T1 - Kalman filter for speech enhancement in cocktail party scenarios using a codebook-based approach

AU - Kavalekalam, Mathew Shaji

AU - Christensen, Mads Græsbøll

AU - Gran, Fredrik

AU - Boldt, Jesper B.

PY - 2016/4

Y1 - 2016/4

N2 - Enhancement of speech in non-stationary background noise is a challenging task, and conventional single channel speech enhancement algorithms have not been able to improve the speech intelligibility in such scenarios. The work proposed in this paper investigates a single channel Kalman filter based speech enhancement algorithm, whose parameters are estimated using a codebook based approach. The results indicate that the enhancement algorithm is able to improve the speech intelligibility and quality according to objective measures. Moreover, we investigate the effects of utilizing a speaker specific trained codebook over a generic speech codebook in relation to the performance of the speech enhancement system.

AB - Enhancement of speech in non-stationary background noise is a challenging task, and conventional single channel speech enhancement algorithms have not been able to improve the speech intelligibility in such scenarios. The work proposed in this paper investigates a single channel Kalman filter based speech enhancement algorithm, whose parameters are estimated using a codebook based approach. The results indicate that the enhancement algorithm is able to improve the speech intelligibility and quality according to objective measures. Moreover, we investigate the effects of utilizing a speaker specific trained codebook over a generic speech codebook in relation to the performance of the speech enhancement system.

U2 - 10.1109/ICASSP.2016.7471663

DO - 10.1109/ICASSP.2016.7471663

M3 - Conference article in Journal

SN - 1520-6149

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

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

T2 - The 41st IEEE International Conference on Acoustics, Speech and Signal Processing

Y2 - 20 March 2016 through 25 March 2016

ER -

Kalman filter for speech enhancement in cocktail party scenarios using a codebook-based approach

Abstract

Conference

Access to Document

AUB Link

Fingerprint

Cite this