Noise Suppression Based On Wavelet Packet Decomposition and Quantile Noise Estimation For Robust Automatic Speech Recognition

Erhard Rank; Van Tuan Pham; Gernot Kubin

doi:10.1109/ICASSP.2006.1660061

Noise Suppression Based On Wavelet Packet Decomposition and Quantile Noise Estimation For Robust Automatic Speech Recognition

Erhard Rank, Van Tuan Pham, Gernot Kubin

Institut für Signalverarbeitung und Sprachkommunikation (4420)

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Abstract

In this paper we address the application of a denoising algorithm based on wavelet packet decomposition and quantile noise estimation to noise suppression for automatic speech recognition. The denoising algorithm is adapted to suit the different requirements in machine recognition, as compared to human perception, and is tested in combination with state-of-the-art speech recognition systems. The results show, that, if the proposed algorithm is integrated with the recognition system - including the training process - a performance comparable to recent high-quality noise suppression methods is achieved

Originalsprache	englisch
Titel	2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings
Seiten	477-480
DOIs	https://doi.org/10.1109/ICASSP.2006.1660061
Publikationsstatus	Veröffentlicht - 2006
Veranstaltung	2006 IEEE International Conference on Acoustics, Speech and Signal Processing: ICASSP 2006 - Toulouse, Frankreich Dauer: 14 Mai 2006 → 19 Mai 2006

Konferenz

Konferenz	2006 IEEE International Conference on Acoustics, Speech and Signal Processing
Land/Gebiet	Frankreich
Ort	Toulouse
Zeitraum	14/05/06 → 19/05/06

Treatment code (Nähere Zuordnung)

Application
Basic - Fundamental (Grundlagenforschung)

Zugriff auf Dokument

10.1109/ICASSP.2006.1660061

icassp06_rank_pham.pdfAkzeptiertes Autorenmanuskript, 402 KB

EU - SNOW - Services for nomadic workers
Pham, V. T., Rank, E. & Kubin, G.
1/10/04 → 30/09/06
Projekt: Forschungsprojekt

Dieses zitieren

Noise Suppression Based On Wavelet Packet Decomposition and Quantile Noise Estimation For Robust Automatic Speech Recognition. / Rank, Erhard; Pham, Van Tuan; Kubin, Gernot.
2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings. 2006. S. 477-480.

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Rank, E, Pham, VT & Kubin, G 2006, Noise Suppression Based On Wavelet Packet Decomposition and Quantile Noise Estimation For Robust Automatic Speech Recognition. in 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings. S. 477-480, 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, Toulouse, Frankreich, 14/05/06. https://doi.org/10.1109/ICASSP.2006.1660061

@inproceedings{bfc1b401806242aabb27354167d2b1b4,

title = "Noise Suppression Based On Wavelet Packet Decomposition and Quantile Noise Estimation For Robust Automatic Speech Recognition",

abstract = "In this paper we address the application of a denoising algorithm based on wavelet packet decomposition and quantile noise estimation to noise suppression for automatic speech recognition. The denoising algorithm is adapted to suit the different requirements in machine recognition, as compared to human perception, and is tested in combination with state-of-the-art speech recognition systems. The results show, that, if the proposed algorithm is integrated with the recognition system - including the training process - a performance comparable to recent high-quality noise suppression methods is achieved",

author = "Erhard Rank and Pham, {Van Tuan} and Gernot Kubin",

year = "2006",

doi = "10.1109/ICASSP.2006.1660061",

language = "English",

isbn = "1-4244-0469-X",

pages = "477--480",

booktitle = "2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings",

note = "IEEE International Conference on Acoustics, Speech, and Signal Processing : ICASSP 2006 ; Conference date: 14-05-2006 Through 19-05-2006",

}

TY - GEN

T1 - Noise Suppression Based On Wavelet Packet Decomposition and Quantile Noise Estimation For Robust Automatic Speech Recognition

AU - Rank, Erhard

AU - Pham, Van Tuan

AU - Kubin, Gernot

PY - 2006

Y1 - 2006

N2 - In this paper we address the application of a denoising algorithm based on wavelet packet decomposition and quantile noise estimation to noise suppression for automatic speech recognition. The denoising algorithm is adapted to suit the different requirements in machine recognition, as compared to human perception, and is tested in combination with state-of-the-art speech recognition systems. The results show, that, if the proposed algorithm is integrated with the recognition system - including the training process - a performance comparable to recent high-quality noise suppression methods is achieved

AB - In this paper we address the application of a denoising algorithm based on wavelet packet decomposition and quantile noise estimation to noise suppression for automatic speech recognition. The denoising algorithm is adapted to suit the different requirements in machine recognition, as compared to human perception, and is tested in combination with state-of-the-art speech recognition systems. The results show, that, if the proposed algorithm is integrated with the recognition system - including the training process - a performance comparable to recent high-quality noise suppression methods is achieved

U2 - 10.1109/ICASSP.2006.1660061

DO - 10.1109/ICASSP.2006.1660061

M3 - Conference paper

SN - 1-4244-0469-X

SP - 477

EP - 480

BT - 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings

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

Y2 - 14 May 2006 through 19 May 2006

ER -

Noise Suppression Based On Wavelet Packet Decomposition and Quantile Noise Estimation For Robust Automatic Speech Recognition

Abstract

Konferenz

Treatment code (Nähere Zuordnung)

Zugriff auf Dokument

Fingerprint

Projekte

EU - SNOW - Services for nomadic workers

Dieses zitieren