Summary
|
For Full-Text PDF, please login, if you are a member of IEICE, or go to Pay Per View on menu list, if you are a nonmember of IEICE. |
|
Production-Oriented Models for Speech Recognition Erik MCDERMOTT Atsushi NAKAMURA Publication IEICE TRANSACTIONS on Information and Systems Vol.E89-D No.3 pp.1006-1014 Publication Date: 2006/03/01 Online ISSN: 1745-1361 DOI: 10.1093/ietisy/e89-d.3.1006 Print ISSN: 0916-8532 Type of Manuscript: Special Section PAPER (Special Section on Statistical Modeling for Speech Processing) Category: Speech Recognition Keyword: speech recognition, speech production, articulatory modeling, linear dynamical systems, Full Text: PDF(566.6KB)>>
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. | ||||||||||
| ||||||||||
