First experiments on an HMM based double layer framework for automatic continuous speech recognition
View/Open
Article principal (233,9Kb) (Restricted access)
Request copy
Què és aquest botó?
Aquest botó permet demanar una còpia d'un document restringit a l'autor. Es mostra quan:
- Disposem del correu electrònic de l'autor
- El document té una mida inferior a 20 Mb
- Es tracta d'un document d'accés restringit per decisió de l'autor o d'un document d'accés restringit per política de l'editorial
Document typeConference lecture
Defense date2006
Rights accessRestricted access - publisher's policy
Abstract
The usual approach to automatic continuous speech recognition is what can be called the acoustic-phonetic modelling approach. In this approach, voice is considered
to hold two different kinds of information acoustic and phonetic . Acoustic information is represented by some kind of feature extraction out of the voice signal, and phonetic information is extracted from the vocabulary of the task by means of a lexicon or some other procedure. The
main assumption in this approach is that models can be constructed that capture the correlation existing between
both kinds of information.
The main limitation of acoustic-phonetic modelling in speech recognition is its poor treatment of the variability
present both in the phonetic level and the acoustic one. In this paper, we propose the use of a slightly modified framework where the usual acoustic-phonetic modelling
is divided into two different layers: one closer to the voice signal, and the other closer to the phonetics of the sentence. By doing so we expect an improvement of
the modelling accuracy, as well as a better management of acoustic and phonetic variability. Experiments carried out so far, using a very simpli ed version of the proposed framework, show a signi cant improvement in the recognition of a large vocabulary continuous speech task, and represent a promising start point for
future research.
CitationNogueiras, A. [et al.]. First experiments on an HMM based double layer framework for automatic continuous speech recognition. A: Jornadas en Tecnologia del Habla. "Actas de las IV Jornadas en Tecnologia del Habla". Zaragoza: 2006, p. 225-229.
ISBN84-96214-82-6
Publisher versionhttp://jth2006.unizar.es/finals/4jth_162.pdf
Files | Description | Size | Format | View |
---|---|---|---|---|
4jth_162.pdf![]() | Article principal | 233,9Kb | Restricted access |
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder