Automatic phoneme-level segmentation and transcription of the Filipino speech corpus using split temporal context and hybrid-HMM network architecture

Automatic Speech Recognition (ASR) systems are very valuable in developing large vocabulary speech corpora which are primarily used in the human-machine communication technology. In this project, the objective is to develop a method for automatic phoneme-level segmentation and transcription of the F...

ver descrição completa

Detalhes bibliográficos

Autor principal:	Mendoza, Joseph Christian B.
Outros Autores:	Morales, Michael S.
Formato:	Tese
Idioma:	English
Publicado em:	2008.
Assuntos:	Automatic speech recognition. Computer network architectures. Speech processing > Digital techniques. Filipino speech corpus. Hybrid-HMM network architecture.