Please use this identifier to cite or link to this item:
Title: Towards multilingual speech recognition using data driven source/target acoustical units association
Authors: Bayeh, Rania
Lin, Shiuan-Sung
Mokbel, Chafic 
Chollet, Gérard
Affiliations: Department of Electrical Engineering 
Keywords: Speech recognition
Natural languages
Subjects: Databases
Automatic speech recognition
Issue Date: 2004
Conference: IEEE International Conference on Acoustics, Speech and Signal Processing (17-21 May 2004 : Canada) 
Multilingual speech recognition pushes to us study the acoustic modeling of target language units using one or more source languages' units. This paper presents a study of manual and data driven association of two possible target units with source language's phonemes. The target units studied are words and phonemes. Algorithms for data-driven association are described. While phoneme-to-phoneme association is more practical, words' transcription provides better results. It has been shown that more precise and rich source models are more suitable to determine those association. Experiments are conducted with French as source language and Arabic as target language.
Ezproxy URL: Link to full text
Type: Conference Paper
Appears in Collections:Department of Electrical Engineering

Show full item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.