Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition

Nobuhide Yamakawa; Tetsuro Kitahara; Toru Takahashi; Kazunori Komatani; Tetsuya Ogata; Hiroshi G. Okuno

Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition

Nobuhide Yamakawa, Tetsuro Kitahara, Toru Takahashi, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

School of Fundamental Science and Engineering

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

11 Citations (Scopus)

Abstract

Research on environmental sound recognition has not shown great development in comparison with that on speech and musical signals. One of the reasons is that the sound category of environmental sounds covers a broad range of acoustical natures. We classified them in order to explore suitable recognition techniques for each characteristic. We focus on impulsive sounds and their non-stationary feature within and between analytic frames. We used matching-pursuit as a framework to use wavelet analysis for extracting temporal variation of audio features inside a frame. We also investigated the validity of modeling decaying patterns of sounds using Hidden markov models. Experimental results indicate that sounds with multiple impulsive signals are recognized better by using time-frequency analyzing bases than by frequency domain analysis. Classification of sound classes with a long and clear decaying pattern improves when HMMs with multiple number of hidden states are applied.

Original language	English
Title of host publication	Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
Publisher	International Speech Communication Association
Pages	2342-2345
Number of pages	4
Publication status	Published - 2010

Publication series

Name	Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

Keywords

Audio signal classification
Environmental sound recognition
Matching-pursuit
Non-speech sound recognition
Time-frequency analysis

ASJC Scopus subject areas

Language and Linguistics
Speech and Hearing

Fingerprint Dive into the research topics of 'Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition'. Together they form a unique fingerprint.

Cite this

Yamakawa, N., Kitahara, T., Takahashi, T., Komatani, K., Ogata, T., & Okuno, H. G. (2010). Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 (pp. 2342-2345). (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010). International Speech Communication Association.

Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition. / Yamakawa, Nobuhide; Kitahara, Tetsuro; Takahashi, Toru; Komatani, Kazunori; Ogata, Tetsuya; Okuno, Hiroshi G.

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association, 2010. p. 2342-2345 (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

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

Yamakawa, N, Kitahara, T, Takahashi, T, Komatani, K, Ogata, T & Okuno, HG 2010, Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition. in Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010, International Speech Communication Association, pp. 2342-2345.

Yamakawa N, Kitahara T, Takahashi T, Komatani K, Ogata T, Okuno HG. Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association. 2010. p. 2342-2345. (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

Yamakawa, Nobuhide ; Kitahara, Tetsuro ; Takahashi, Toru ; Komatani, Kazunori ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. International Speech Communication Association, 2010. pp. 2342-2345 (Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010).

@inproceedings{a13c0f87dbfd4c6599595ea6b940220d,

title = "Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition",

abstract = "Research on environmental sound recognition has not shown great development in comparison with that on speech and musical signals. One of the reasons is that the sound category of environmental sounds covers a broad range of acoustical natures. We classified them in order to explore suitable recognition techniques for each characteristic. We focus on impulsive sounds and their non-stationary feature within and between analytic frames. We used matching-pursuit as a framework to use wavelet analysis for extracting temporal variation of audio features inside a frame. We also investigated the validity of modeling decaying patterns of sounds using Hidden markov models. Experimental results indicate that sounds with multiple impulsive signals are recognized better by using time-frequency analyzing bases than by frequency domain analysis. Classification of sound classes with a long and clear decaying pattern improves when HMMs with multiple number of hidden states are applied.",

keywords = "Audio signal classification, Environmental sound recognition, Matching-pursuit, Non-speech sound recognition, Time-frequency analysis",

author = "Nobuhide Yamakawa and Tetsuro Kitahara and Toru Takahashi and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",

year = "2010",

language = "English",

series = "Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010",

publisher = "International Speech Communication Association",

pages = "2342--2345",

booktitle = "Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010",

}

TY - GEN

T1 - Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition

AU - Yamakawa, Nobuhide

AU - Kitahara, Tetsuro

AU - Takahashi, Toru

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2010

Y1 - 2010

N2 - Research on environmental sound recognition has not shown great development in comparison with that on speech and musical signals. One of the reasons is that the sound category of environmental sounds covers a broad range of acoustical natures. We classified them in order to explore suitable recognition techniques for each characteristic. We focus on impulsive sounds and their non-stationary feature within and between analytic frames. We used matching-pursuit as a framework to use wavelet analysis for extracting temporal variation of audio features inside a frame. We also investigated the validity of modeling decaying patterns of sounds using Hidden markov models. Experimental results indicate that sounds with multiple impulsive signals are recognized better by using time-frequency analyzing bases than by frequency domain analysis. Classification of sound classes with a long and clear decaying pattern improves when HMMs with multiple number of hidden states are applied.

AB - Research on environmental sound recognition has not shown great development in comparison with that on speech and musical signals. One of the reasons is that the sound category of environmental sounds covers a broad range of acoustical natures. We classified them in order to explore suitable recognition techniques for each characteristic. We focus on impulsive sounds and their non-stationary feature within and between analytic frames. We used matching-pursuit as a framework to use wavelet analysis for extracting temporal variation of audio features inside a frame. We also investigated the validity of modeling decaying patterns of sounds using Hidden markov models. Experimental results indicate that sounds with multiple impulsive signals are recognized better by using time-frequency analyzing bases than by frequency domain analysis. Classification of sound classes with a long and clear decaying pattern improves when HMMs with multiple number of hidden states are applied.

KW - Audio signal classification

KW - Environmental sound recognition

KW - Matching-pursuit

KW - Non-speech sound recognition

KW - Time-frequency analysis

UR - http://www.scopus.com/inward/record.url?scp=79959833649&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959833649&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:79959833649

T3 - Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

SP - 2342

EP - 2345

BT - Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

PB - International Speech Communication Association

ER -