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

Institute of Signal Processing and Speech Communication (4420)

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

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

Original language	English
Title of host publication	2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings
Pages	477-480
DOIs	https://doi.org/10.1109/ICASSP.2006.1660061
Publication status	Published - 2006
Event	IEEE International Conference on Acoustics, Speech, and Signal Processing: ICASSP 2006 - Toulouse, France Duration: 14 May 2006 → 19 May 2006

Conference

Conference	IEEE International Conference on Acoustics, Speech, and Signal Processing
Country/Territory	France
City	Toulouse
Period	14/05/06 → 19/05/06

Treatment code (Nähere Zuordnung)

Application
Basic - Fundamental (Grundlagenforschung)

Access to Document

10.1109/ICASSP.2006.1660061

icassp06_rank_pham.pdfAccepted author manuscript, 402 KB

EU - SNOW - Services for NOmadic Workers
Kubin, G. (Project manager), Pham, V. T. (Attendee / Assistant) & Rank, E. (Coordinator)
1/10/04 → 30/09/06
Project: Research project

Cite this

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. p. 477-480.

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

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. pp. 477-480, IEEE International Conference on Acoustics, Speech, and Signal Processing, Toulouse, France, 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

Conference

Treatment code (Nähere Zuordnung)

Access to Document

Fingerprint

Projects

EU - SNOW - Services for NOmadic Workers

Cite this