A blind separation of monaural sound based on peak tracking of frequency spectra

Shoko Yamahata; Mitsuharu Matsumoto; Shuji Hashimoto

doi:10.1109/ICIME.2009.33

A blind separation of monaural sound based on peak tracking of frequency spectra

Shoko Yamahata^*, 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 a blind separation algorithm of monaural sound based on peak tracking of frequency spectra. We have already reported a blind separation method based on the change ratio of frequency components. However it cannot handle a signal with frequency fluctuation such as a speech signal or a vibrato tone, because such type of signal is regarded as the mixture of different sounds. Our new method proposed in this paper can handle a sound with frequency fluctuation by tracking frequency peaks along time axis. The effectiveness of the proposed method is evaluated with some experiments on real voice data.

Original language	English
Title of host publication	Proceedings - 2009 International Conference on Information Management and Engineering, ICIME 2009
Pages	305-311
Number of pages	7
DOIs	https://doi.org/10.1109/ICIME.2009.33
Publication status	Published - 2009
Event	2009 International Conference on Information Management and Engineering, ICIME 2009 - Kuala Lumpur Duration: 2009 Apr 3 → 2009 Apr 5

Other

Other	2009 International Conference on Information Management and Engineering, ICIME 2009
City	Kuala Lumpur
Period	09/4/3 → 09/4/5

ASJC Scopus subject areas

Computer Science Applications
Information Systems
Information Systems and Management

Access to Document

10.1109/ICIME.2009.33

Cite this

Yamahata, S, Matsumoto, M & Hashimoto, S 2009, A blind separation of monaural sound based on peak tracking of frequency spectra. in Proceedings - 2009 International Conference on Information Management and Engineering, ICIME 2009., 5077048, pp. 305-311, 2009 International Conference on Information Management and Engineering, ICIME 2009, Kuala Lumpur, 09/4/3. https://doi.org/10.1109/ICIME.2009.33

@inproceedings{7d2e0cb679794a36b114e4f014dc4cf9,

title = "A blind separation of monaural sound based on peak tracking of frequency spectra",

abstract = "This paper describes a blind separation algorithm of monaural sound based on peak tracking of frequency spectra. We have already reported a blind separation method based on the change ratio of frequency components. However it cannot handle a signal with frequency fluctuation such as a speech signal or a vibrato tone, because such type of signal is regarded as the mixture of different sounds. Our new method proposed in this paper can handle a sound with frequency fluctuation by tracking frequency peaks along time axis. The effectiveness of the proposed method is evaluated with some experiments on real voice data.",

author = "Shoko Yamahata and Mitsuharu Matsumoto and Shuji Hashimoto",

year = "2009",

doi = "10.1109/ICIME.2009.33",

language = "English",

isbn = "9780769535951",

pages = "305--311",

booktitle = "Proceedings - 2009 International Conference on Information Management and Engineering, ICIME 2009",

note = "2009 International Conference on Information Management and Engineering, ICIME 2009 ; Conference date: 03-04-2009 Through 05-04-2009",

}

TY - GEN

T1 - A blind separation of monaural sound based on peak tracking of frequency spectra

AU - Yamahata, Shoko

AU - Matsumoto, Mitsuharu

AU - Hashimoto, Shuji

PY - 2009

Y1 - 2009

N2 - This paper describes a blind separation algorithm of monaural sound based on peak tracking of frequency spectra. We have already reported a blind separation method based on the change ratio of frequency components. However it cannot handle a signal with frequency fluctuation such as a speech signal or a vibrato tone, because such type of signal is regarded as the mixture of different sounds. Our new method proposed in this paper can handle a sound with frequency fluctuation by tracking frequency peaks along time axis. The effectiveness of the proposed method is evaluated with some experiments on real voice data.

AB - This paper describes a blind separation algorithm of monaural sound based on peak tracking of frequency spectra. We have already reported a blind separation method based on the change ratio of frequency components. However it cannot handle a signal with frequency fluctuation such as a speech signal or a vibrato tone, because such type of signal is regarded as the mixture of different sounds. Our new method proposed in this paper can handle a sound with frequency fluctuation by tracking frequency peaks along time axis. The effectiveness of the proposed method is evaluated with some experiments on real voice data.

UR - http://www.scopus.com/inward/record.url?scp=70349506305&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349506305&partnerID=8YFLogxK

U2 - 10.1109/ICIME.2009.33

DO - 10.1109/ICIME.2009.33

M3 - Conference contribution

AN - SCOPUS:70349506305

SN - 9780769535951

SP - 305

EP - 311

BT - Proceedings - 2009 International Conference on Information Management and Engineering, ICIME 2009

T2 - 2009 International Conference on Information Management and Engineering, ICIME 2009

Y2 - 3 April 2009 through 5 April 2009

ER -

A blind separation of monaural sound based on peak tracking of frequency spectra

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this