Due to the enormous development of large vocabulary, speaker-independent continuous speech recognition systems, which occur essentially for the US English language, there is a large demand of this kind of systems for other languages. In this paper we present the work done in the development of a large vocabulary, speaker-independent continuous speech recognition hybrid system for the European Portuguese language. This is a difficult task due to the basic development stage of this technology in the European Portuguese language. The development of a system of this kind for a new language depends on the availability of the appropriate source components, mainly a speech corpus and large amounts of texts. This work became possible due to the development of a new database (BD-PUBLICO), a large vocabulary speech corpus for the European Portuguese language developed by us over the last two years.
[1]
Ciro Martins,et al.
An incremental speaker-adaptation technique for hybrid HMM-MLP recognizer
,
1996,
Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.
[2]
Ciro Martins,et al.
The development of a speaker independent continuous speech recognizer for portuguese
,
1997,
EUROSPEECH.
[3]
W. Fisher,et al.
An acoustic‐phonetic data base
,
1987
.
[4]
Danny Kershaw,et al.
Phonetic Context-Dependency In a Hybrid ANN/HMM Speech Recognition System
,
1997
.
[5]
Ciro Martins,et al.
The design of a large vocabulary speech corpus for portuguese
,
1997,
EUROSPEECH.
[6]
Hervé Bourlard,et al.
Connectionist Speech Recognition: A Hybrid Approach
,
1993
.