Production-Oriented Models for Speech Recognition
Summary :
Acoustic modeling in speech recognition uses very little knowledge of the speech production process. At many levels our models continue to model speech as a surface phenomenon. Typically, hidden Markov model (HMM) parameters operate primarily in the acoustic space or in a linear transformation thereof; state-to-state evolution is modeled only crudely, with no explicit relationship between states, such as would be afforded by the use of phonetic features commonly used by linguists to describe speech phenomena, or by the continuity and smoothness of the production parameters governing speech. This survey article attempts to provide an overview of proposals by several researchers for improving acoustic modeling in these regards. Such topics as the controversial Motor Theory of Speech Perception, work by Hogden explicitly using a continuity constraint in a pseudo-articulatory domain, the Kalman filter based Hidden Dynamic Model, and work by many groups showing the benefits of using articulatory features instead of phones as the underlying units of speech, will be covered.
- Publication
- IEICE TRANSACTIONS on Information Vol.E89-D No.3 pp.1006-1014
- Publication Date
- 2006/03/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1093/ietisy/e89-d.3.1006
- Type of Manuscript
- Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
- Category
- Speech Recognition
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Erik MCDERMOTT, Atsushi NAKAMURA, "Production-Oriented Models for Speech Recognition" in IEICE TRANSACTIONS on Information,
vol. E89-D, no. 3, pp. 1006-1014, March 2006, doi: 10.1093/ietisy/e89-d.3.1006.
Abstract: Acoustic modeling in speech recognition uses very little knowledge of the speech production process. At many levels our models continue to model speech as a surface phenomenon. Typically, hidden Markov model (HMM) parameters operate primarily in the acoustic space or in a linear transformation thereof; state-to-state evolution is modeled only crudely, with no explicit relationship between states, such as would be afforded by the use of phonetic features commonly used by linguists to describe speech phenomena, or by the continuity and smoothness of the production parameters governing speech. This survey article attempts to provide an overview of proposals by several researchers for improving acoustic modeling in these regards. Such topics as the controversial Motor Theory of Speech Perception, work by Hogden explicitly using a continuity constraint in a pseudo-articulatory domain, the Kalman filter based Hidden Dynamic Model, and work by many groups showing the benefits of using articulatory features instead of phones as the underlying units of speech, will be covered.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.3.1006/_p
Copy
@ARTICLE{e89-d_3_1006,
author={Erik MCDERMOTT, Atsushi NAKAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Production-Oriented Models for Speech Recognition},
year={2006},
volume={E89-D},
number={3},
pages={1006-1014},
abstract={Acoustic modeling in speech recognition uses very little knowledge of the speech production process. At many levels our models continue to model speech as a surface phenomenon. Typically, hidden Markov model (HMM) parameters operate primarily in the acoustic space or in a linear transformation thereof; state-to-state evolution is modeled only crudely, with no explicit relationship between states, such as would be afforded by the use of phonetic features commonly used by linguists to describe speech phenomena, or by the continuity and smoothness of the production parameters governing speech. This survey article attempts to provide an overview of proposals by several researchers for improving acoustic modeling in these regards. Such topics as the controversial Motor Theory of Speech Perception, work by Hogden explicitly using a continuity constraint in a pseudo-articulatory domain, the Kalman filter based Hidden Dynamic Model, and work by many groups showing the benefits of using articulatory features instead of phones as the underlying units of speech, will be covered.},
keywords={},
doi={10.1093/ietisy/e89-d.3.1006},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Production-Oriented Models for Speech Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1006
EP - 1014
AU - Erik MCDERMOTT
AU - Atsushi NAKAMURA
PY - 2006
DO - 10.1093/ietisy/e89-d.3.1006
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2006
AB - Acoustic modeling in speech recognition uses very little knowledge of the speech production process. At many levels our models continue to model speech as a surface phenomenon. Typically, hidden Markov model (HMM) parameters operate primarily in the acoustic space or in a linear transformation thereof; state-to-state evolution is modeled only crudely, with no explicit relationship between states, such as would be afforded by the use of phonetic features commonly used by linguists to describe speech phenomena, or by the continuity and smoothness of the production parameters governing speech. This survey article attempts to provide an overview of proposals by several researchers for improving acoustic modeling in these regards. Such topics as the controversial Motor Theory of Speech Perception, work by Hogden explicitly using a continuity constraint in a pseudo-articulatory domain, the Kalman filter based Hidden Dynamic Model, and work by many groups showing the benefits of using articulatory features instead of phones as the underlying units of speech, will be covered.
ER -
English
