Parameter setting of noise reduction filter using speech recognition system

Tomomi Abe; Mitsuharu Matsumoto; Shuji Hashimoto

Parameter setting of noise reduction filter using speech recognition system

Tomomi Abe^*, Mitsuharu Matsumoto, Shuji Hashimoto

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

This paper describes parameter setting of noise reduction filter using speech recognition system. Parameter setting problem is usually solved by maximization or minimization of some objective evaluation functions such as correlation and statistical independence. However, when we consider a single-channel noisy signal, it is difficult to employ such objective functions. It is also difficult to employ them when we consider impulsive noise because its duration is very small to use this assumption. To solve the problems, we directly use a speech recognition system as evaluation function for parameter setting. As an example, we employ time-frequency e-filter and Julius as a filtering system and a speech recognition system, respectively. The experimental results show that the proposed approach has a potential to set the parameter in unknown environments.

Original language	English
Title of host publication	ICFC 2010 ICNC 2010 - Proceedings of the International Conference on Fuzzy Computation and International Conference on Neural Computation
Pages	387-391
Number of pages	5
Publication status	Published - 2010
Event	International Conference on Neural Computation, ICNC 2010 and of the International Conference on Fuzzy Computation, ICFC 2010 - Valencia Duration: 2010 Oct 24 → 2010 Oct 26

Other

Other	International Conference on Neural Computation, ICNC 2010 and of the International Conference on Fuzzy Computation, ICFC 2010
City	Valencia
Period	10/10/24 → 10/10/26

Keywords

Nonlinear filter
Parameter optimization
Recognition-based approach
Speech recognition system

ASJC Scopus subject areas

Computational Theory and Mathematics
Applied Mathematics

Cite this

Parameter setting of noise reduction filter using speech recognition system. / Abe, Tomomi; Matsumoto, Mitsuharu; Hashimoto, Shuji.

ICFC 2010 ICNC 2010 - Proceedings of the International Conference on Fuzzy Computation and International Conference on Neural Computation. 2010. p. 387-391.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abe, T, Matsumoto, M & Hashimoto, S 2010, Parameter setting of noise reduction filter using speech recognition system. in ICFC 2010 ICNC 2010 - Proceedings of the International Conference on Fuzzy Computation and International Conference on Neural Computation. pp. 387-391, International Conference on Neural Computation, ICNC 2010 and of the International Conference on Fuzzy Computation, ICFC 2010, Valencia, 10/10/24.

@inproceedings{fdcb08711fb2488a94e244fb67aaa1fb,

title = "Parameter setting of noise reduction filter using speech recognition system",

abstract = "This paper describes parameter setting of noise reduction filter using speech recognition system. Parameter setting problem is usually solved by maximization or minimization of some objective evaluation functions such as correlation and statistical independence. However, when we consider a single-channel noisy signal, it is difficult to employ such objective functions. It is also difficult to employ them when we consider impulsive noise because its duration is very small to use this assumption. To solve the problems, we directly use a speech recognition system as evaluation function for parameter setting. As an example, we employ time-frequency e-filter and Julius as a filtering system and a speech recognition system, respectively. The experimental results show that the proposed approach has a potential to set the parameter in unknown environments.",

keywords = "Nonlinear filter, Parameter optimization, Recognition-based approach, Speech recognition system",

author = "Tomomi Abe and Mitsuharu Matsumoto and Shuji Hashimoto",

year = "2010",

language = "English",

isbn = "9789898425324",

pages = "387--391",

booktitle = "ICFC 2010 ICNC 2010 - Proceedings of the International Conference on Fuzzy Computation and International Conference on Neural Computation",

note = "International Conference on Neural Computation, ICNC 2010 and of the International Conference on Fuzzy Computation, ICFC 2010 ; Conference date: 24-10-2010 Through 26-10-2010",

}

TY - GEN

T1 - Parameter setting of noise reduction filter using speech recognition system

AU - Abe, Tomomi

AU - Matsumoto, Mitsuharu

AU - Hashimoto, Shuji

PY - 2010

Y1 - 2010

N2 - This paper describes parameter setting of noise reduction filter using speech recognition system. Parameter setting problem is usually solved by maximization or minimization of some objective evaluation functions such as correlation and statistical independence. However, when we consider a single-channel noisy signal, it is difficult to employ such objective functions. It is also difficult to employ them when we consider impulsive noise because its duration is very small to use this assumption. To solve the problems, we directly use a speech recognition system as evaluation function for parameter setting. As an example, we employ time-frequency e-filter and Julius as a filtering system and a speech recognition system, respectively. The experimental results show that the proposed approach has a potential to set the parameter in unknown environments.

AB - This paper describes parameter setting of noise reduction filter using speech recognition system. Parameter setting problem is usually solved by maximization or minimization of some objective evaluation functions such as correlation and statistical independence. However, when we consider a single-channel noisy signal, it is difficult to employ such objective functions. It is also difficult to employ them when we consider impulsive noise because its duration is very small to use this assumption. To solve the problems, we directly use a speech recognition system as evaluation function for parameter setting. As an example, we employ time-frequency e-filter and Julius as a filtering system and a speech recognition system, respectively. The experimental results show that the proposed approach has a potential to set the parameter in unknown environments.

KW - Nonlinear filter

KW - Parameter optimization

KW - Recognition-based approach

KW - Speech recognition system

UR - http://www.scopus.com/inward/record.url?scp=78651420954&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651420954&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78651420954

SN - 9789898425324

SP - 387

EP - 391

BT - ICFC 2010 ICNC 2010 - Proceedings of the International Conference on Fuzzy Computation and International Conference on Neural Computation

T2 - International Conference on Neural Computation, ICNC 2010 and of the International Conference on Fuzzy Computation, ICFC 2010

Y2 - 24 October 2010 through 26 October 2010

ER -

Parameter setting of noise reduction filter using speech recognition system

Abstract

Other

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this