Models of Phonetic Recognition III: The Role of Analysis by Synthesis in Phonetic Recognition

Auteurs-es

  • Victor W. Zue

Résumé

This paper proposes a recognition model that attempts to deal with variabilities found in the acoustic signal. The input speech signal is first transformed into a representation that takes into account known properties of the human auditory system. From various stages of this transformation, acoustic parameters are extracted and used to classify the utterance into broad phonetic categories. The outcome of this analysis is used for lexical access. The constraints imposed by the language on possible sound patterns should significantly reduce the number of word candidates. Finally, detailed acoustic cues will be utilised to select the correct word from the small set of candidate words.

Fichiers supplémentaires

Publié-e

2022-12-03

Comment citer

1.
Zue VW. Models of Phonetic Recognition III: The Role of Analysis by Synthesis in Phonetic Recognition. Canadian Acoustics [Internet]. 3 déc. 2022 [cité 21 nov. 2024];14(3 bis):69-70. Disponible à: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/3526

Numéro

Rubrique

Actes du congrès de la Semaine canadienne d'acoustique