Neural network classifier architectures for phoneme recognition / by William Treurniet. : Co24-3/8-1992-1E-PDF
"Automatic recognition of words in continuous speech is difficult to do with whole-word template models, especially when the vocabulary is reasonably large. Instead, the currently preferred approaches for this task hypothesize the presence of words or sub-words, such as syllables or phonemes, on the basis of likelihood estimates obtained from comparisons of the acoustic data with statistical models derived from training data. This paper is concerned with the application of artificial neural networks, trained with the back-propagation learning algorithm, to modelling phonemes extracted from the DARPA TIMIT multi-speaker, continuous speech data base"--Abstract.
Lien permanent pour cette publication :
publications.gc.ca/pub?id=9.890766&sl=1
Ministère/Organisme | Communications Research Centre (Canada), issuing body. |
---|---|
Titre | Neural network classifier architectures for phoneme recognition / by William Treurniet. |
Titre de la série | CRC technical note ; no. CRC-TN-92-001 |
Type de publication | Série - Voir l'enregistrement principal |
Langue | [Anglais] |
Format | Électronique |
Document électronique | |
Note(s) | "Ottawa, March 26, 1992." Digitized edition from print [produced by Innovation, Science and Economic Development Canada]. Includes bibliographical references (pages 36-38). Issued also in print format. Includes abstracts in English and French. |
Information sur la publication | Ottawa : Communications Research Centre, Broadcast Technologies Research = Centre de recherches sur les communications, Recherche en technologies de radiodiffusion, 1992. ©1992. |
Auteur / Contributeur | Treurniet, W. C. (William C.)author. |
Description | 1 online resource (iii, 38 pages) : illustrations. |
Numéro de catalogue |
|
Descripteurs | Automatic speech recognition. Neural networks (Computer science) Reconnaissance automatique de la parole. Réseaux neuronaux (Informatique) |