An auto-regressive, non-stationary excited signal parameter estimation method and an evaluation of a singing-voice recognition

Akira Sasou; Masataka Goto; Satoru Hayamizu; Kazuyo Tanaka

doi:10.1109/ICASSP.2005.1415094

An auto-regressive, non-stationary excited signal parameter estimation method and an evaluation of a singing-voice recognition

Akira Sasou^*, Masataka Goto, Satoru Hayamizu, Kazuyo Tanaka

^*Corresponding author for this work

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

13 Citations (Scopus)

Abstract

We have previously described an Auto-Regressive Hidden Markov Model (AR-HMM) and an accompanying parameter estimation method. The AR-HMM was obtained by combining an AR process with an HMM introduced as a non-stationary excitation model. We demonstrated that the AR-HMM can accurately estimate the characteristics of both articulatory systems and excitation signals from high-pitched speech. In this paper, we apply the AR-HMM to feature extraction from singing voices and evaluate the recognition accuracy of the AR-HMM-based approach.

Original language	English
Title of host publication	2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	I237-I240
ISBN (Print)	0780388747, 9780780388741
DOIs	https://doi.org/10.1109/ICASSP.2005.1415094
Publication status	Published - 2005
Externally published	Yes
Event	2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Philadelphia, PA, United States Duration: 2005 Mar 18 → 2005 Mar 23

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	I
ISSN (Print)	1520-6149

Conference

Conference	2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05
Country/Territory	United States
City	Philadelphia, PA
Period	05/3/18 → 05/3/23

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2005.1415094

Cite this

Sasou, A., Goto, M., Hayamizu, S., & Tanaka, K. (2005). An auto-regressive, non-stationary excited signal parameter estimation method and an evaluation of a singing-voice recognition. In 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing (pp. I237-I240). Article 1415094 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. I). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2005.1415094

An auto-regressive, non-stationary excited signal parameter estimation method and an evaluation of a singing-voice recognition. / Sasou, Akira; Goto, Masataka; Hayamizu, Satoru et al.
2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing. Institute of Electrical and Electronics Engineers Inc., 2005. p. I237-I240 1415094 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. I).

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

Sasou, A, Goto, M, Hayamizu, S & Tanaka, K 2005, An auto-regressive, non-stationary excited signal parameter estimation method and an evaluation of a singing-voice recognition. in 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing., 1415094, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. I, Institute of Electrical and Electronics Engineers Inc., pp. I237-I240, 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05, Philadelphia, PA, United States, 05/3/18. https://doi.org/10.1109/ICASSP.2005.1415094

Sasou A, Goto M, Hayamizu S, Tanaka K. An auto-regressive, non-stationary excited signal parameter estimation method and an evaluation of a singing-voice recognition. In 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing. Institute of Electrical and Electronics Engineers Inc. 2005. p. I237-I240. 1415094. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2005.1415094

Sasou, Akira ; Goto, Masataka ; Hayamizu, Satoru et al. / An auto-regressive, non-stationary excited signal parameter estimation method and an evaluation of a singing-voice recognition. 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing. Institute of Electrical and Electronics Engineers Inc., 2005. pp. I237-I240 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{5f905d8e25e6457b8364dd7c3ae7488e,

title = "An auto-regressive, non-stationary excited signal parameter estimation method and an evaluation of a singing-voice recognition",

abstract = "We have previously described an Auto-Regressive Hidden Markov Model (AR-HMM) and an accompanying parameter estimation method. The AR-HMM was obtained by combining an AR process with an HMM introduced as a non-stationary excitation model. We demonstrated that the AR-HMM can accurately estimate the characteristics of both articulatory systems and excitation signals from high-pitched speech. In this paper, we apply the AR-HMM to feature extraction from singing voices and evaluate the recognition accuracy of the AR-HMM-based approach.",

author = "Akira Sasou and Masataka Goto and Satoru Hayamizu and Kazuyo Tanaka",

year = "2005",

doi = "10.1109/ICASSP.2005.1415094",

language = "English",

isbn = "0780388747",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "I237--I240",

booktitle = "2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing",

note = "2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 ; Conference date: 18-03-2005 Through 23-03-2005",

}

TY - GEN

T1 - An auto-regressive, non-stationary excited signal parameter estimation method and an evaluation of a singing-voice recognition

AU - Sasou, Akira

AU - Goto, Masataka

AU - Hayamizu, Satoru

AU - Tanaka, Kazuyo

PY - 2005

Y1 - 2005

N2 - We have previously described an Auto-Regressive Hidden Markov Model (AR-HMM) and an accompanying parameter estimation method. The AR-HMM was obtained by combining an AR process with an HMM introduced as a non-stationary excitation model. We demonstrated that the AR-HMM can accurately estimate the characteristics of both articulatory systems and excitation signals from high-pitched speech. In this paper, we apply the AR-HMM to feature extraction from singing voices and evaluate the recognition accuracy of the AR-HMM-based approach.

AB - We have previously described an Auto-Regressive Hidden Markov Model (AR-HMM) and an accompanying parameter estimation method. The AR-HMM was obtained by combining an AR process with an HMM introduced as a non-stationary excitation model. We demonstrated that the AR-HMM can accurately estimate the characteristics of both articulatory systems and excitation signals from high-pitched speech. In this paper, we apply the AR-HMM to feature extraction from singing voices and evaluate the recognition accuracy of the AR-HMM-based approach.

UR - http://www.scopus.com/inward/record.url?scp=33646802604&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646802604&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2005.1415094

DO - 10.1109/ICASSP.2005.1415094

M3 - Conference contribution

AN - SCOPUS:33646802604

SN - 0780388747

SN - 9780780388741

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - I237-I240

BT - 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 - Proceedings - Image and Multidimensional Signal Processing Multimedia Signal Processing

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05

Y2 - 18 March 2005 through 23 March 2005

ER -

An auto-regressive, non-stationary excited signal parameter estimation method and an evaluation of a singing-voice recognition

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this