Rapid development of an Afrikaans-English speech-to-speech translator
نویسندگان
چکیده
In this paper we investigate the rapid deployment of a twoway Afrikaans to English Speech-to-Speech Translation system. We discuss the approaches and amount of work involved to port a system to a new language pair, i.e. the steps required to rapidly adapt ASR, MT and TTS component to Afrikaans under limited time and data constraints. The resulting system represents the first prototype built for Afrikaans to English speech translation.
منابع مشابه
Using Corpora to Develop Limited-Domain Speech Translation Systems
The paper describes the Spoken Language Translator (SLT) system, a prototype automatic speech translator. SLT is currently capable of translating spoken English queries in the domain of air travel planning into either Swedish or French, using a vocabulary of about 1200 words. We present an overview of the system's architecture, concentrating on how rationally constructed balanced corpora are us...
متن کاملLanguage-dependent State Clustering for Multilingual Speech Recognition in Afrikaans, South African English, Xhosa and Zulu
The development of automatic speech recognition systems requires significant quantities of annotated acoustic data. In South Africa, the large number of spoken languages hampers such data collection efforts. Furthermore, code switching and mixing are commonplace since most citizens speak two or more languages fluently. As a result a considerable degree of phonetic cross pollination between lang...
متن کاملIndividual differences and development of speech act production
This study examined the effects of individual difference (ID) factors on changing pragmatic abilities among L2 learners of English. Participants were 48 Japanese EFL students in an English-medium university in Japan. They completed a pragmatic speaking test (k=12) that assessed their ability to produce two speech acts: requests and opinions, in hi...
متن کاملComparative phonetic analysis and phoneme recognition for Afrikaans, English and Xhosa using the African Speech Technology telephone speech databases
This paper concerns the Afrikaans, English and Xhosa speech databases recently developed as part of the African Speech Technology project. The three corpora are analysed and compared in terms of their phonetic content, diversity and mutual overlap. Connected phoneme recognition systems are subsequently developed and tested in each language.
متن کاملAcoustic modelling of English-accented and Afrikaans-accented South African English
In this paper we investigate whether it is possible to combine speech data from two South African accents of English in order to improve speech recognition in any one accent. Our investigation is based on Afrikaans-accented English and South African English speech data. We compare three acoustic modelling approaches: separate accent-specific models, accentindependent models obtained by straight...
متن کامل