Treinamento de Modelos de Unidades Fonéticas com, Variabilidade Acústica em Reconhecedores de Voz, Continua Baseados em CDHIVIM<br />10.14209/jcis.2000.4
Main Article Content
Abstract
This paper presents several algorithms for training CDHMM-based continuous speech recognizers that use phonetic units with acoustical variability. An algorithm is proposed to solve the problem of mismatching between the phonetic unit models. represented by CDHMM, and the acoustical models. This mismatch arises when the models are trained with the traditional methods employed for sub word units that do not show any significant acoustical variability, such as phones, diphones and triphones.
Article Details
How to Cite
Cerqueira Bispo dos Santos, S., & Alcaim, A. (2015). Treinamento de Modelos de Unidades Fonéticas com, Variabilidade Acústica em Reconhecedores de Voz, Continua Baseados em CDHIVIM<br />10.14209/jcis.2000.4. Journal of Communication and Information Systems, 15(1). Retrieved from https://jcis.sbrt.org.br/jcis/article/view/235
Issue
Section
Regular Papers
Authors who publish in this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) before and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
___________