Determination of articulatory movements from speech acoustics using an HMM-based speech production model

Sadao Hiroya; Masaaki Honda

doi:10.1109/icassp.2002.5743748

Determination of articulatory movements from speech acoustics using an HMM-based speech production model

Sadao Hiroya^*, Masaaki Honda

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

9 Citations (Scopus)

Abstract

We present a method that determines articulatory movements from speech acoustics using an HMM (Hidden Markov Model)-based speech production model. The model statistically generates speech acoustics and articulatory movements from a given phonemic string. It consists of HMMs of articulatory movements for each phoneme and an articulatory-to-acoustic mapping. For a given speech acoustics, maximum likelihood estimation of the articulatory parameters is the statistical model is presented. An experiment was conducted to evaluate the method on sentences, and estimated articulatory parameters were compared with the observed parameters. The rms error of the estimated articulatory parameters is about 2.12 mm on average.

Original language	English
Pages (from-to)	I/437-I/440
Journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	1
DOIs	https://doi.org/10.1109/icassp.2002.5743748
Publication status	Published - 2002
Externally published	Yes
Event	2002 IEEE International Conference on Acustics, Speech, and Signal Processing - Orlando, FL, United States Duration: 2002 May 13 → 2002 May 17

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/icassp.2002.5743748

Cite this

@article{428852b5588c40e9aa17cc5e4f7257fe,

title = "Determination of articulatory movements from speech acoustics using an HMM-based speech production model",

abstract = "We present a method that determines articulatory movements from speech acoustics using an HMM (Hidden Markov Model)-based speech production model. The model statistically generates speech acoustics and articulatory movements from a given phonemic string. It consists of HMMs of articulatory movements for each phoneme and an articulatory-to-acoustic mapping. For a given speech acoustics, maximum likelihood estimation of the articulatory parameters is the statistical model is presented. An experiment was conducted to evaluate the method on sentences, and estimated articulatory parameters were compared with the observed parameters. The rms error of the estimated articulatory parameters is about 2.12 mm on average.",

author = "Sadao Hiroya and Masaaki Honda",

year = "2002",

doi = "10.1109/icassp.2002.5743748",

language = "English",

volume = "1",

pages = "I/437--I/440",

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

issn = "0736-7791",

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

note = "2002 IEEE International Conference on Acustics, Speech, and Signal Processing ; Conference date: 13-05-2002 Through 17-05-2002",

}

TY - JOUR

T1 - Determination of articulatory movements from speech acoustics using an HMM-based speech production model

AU - Hiroya, Sadao

AU - Honda, Masaaki

PY - 2002

Y1 - 2002

N2 - We present a method that determines articulatory movements from speech acoustics using an HMM (Hidden Markov Model)-based speech production model. The model statistically generates speech acoustics and articulatory movements from a given phonemic string. It consists of HMMs of articulatory movements for each phoneme and an articulatory-to-acoustic mapping. For a given speech acoustics, maximum likelihood estimation of the articulatory parameters is the statistical model is presented. An experiment was conducted to evaluate the method on sentences, and estimated articulatory parameters were compared with the observed parameters. The rms error of the estimated articulatory parameters is about 2.12 mm on average.

AB - We present a method that determines articulatory movements from speech acoustics using an HMM (Hidden Markov Model)-based speech production model. The model statistically generates speech acoustics and articulatory movements from a given phonemic string. It consists of HMMs of articulatory movements for each phoneme and an articulatory-to-acoustic mapping. For a given speech acoustics, maximum likelihood estimation of the articulatory parameters is the statistical model is presented. An experiment was conducted to evaluate the method on sentences, and estimated articulatory parameters were compared with the observed parameters. The rms error of the estimated articulatory parameters is about 2.12 mm on average.

UR - http://www.scopus.com/inward/record.url?scp=0036293857&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036293857&partnerID=8YFLogxK

U2 - 10.1109/icassp.2002.5743748

DO - 10.1109/icassp.2002.5743748

M3 - Conference article

AN - SCOPUS:0036293857

SN - 0736-7791

VL - 1

SP - I/437-I/440

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

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

T2 - 2002 IEEE International Conference on Acustics, Speech, and Signal Processing

Y2 - 13 May 2002 through 17 May 2002

ER -

Determination of articulatory movements from speech acoustics using an HMM-based speech production model

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this