Supporting the creation of TTS for local language voice information systems
نویسندگان
چکیده
We report on the Local Language Speech Technology Initiative, which is producing the TTS required for voice information systems in the developing world. We overview the whole process now the initial phases of Hindi, isiZulu, Kiswahili and Ibibio are complete, outline some applications we are targeting, and draw some lessons for the future.
منابع مشابه
Multilingual Voice Creation Toolkit for the MARY TTS Platform
This paper describes an open source voice creation toolkit that supports the creation of unit selection and HMM-based voices, for the MARY (Modular Architecture for Research on speech Synthesis) TTS platform. We aim to provide the tools and generic reusable runtime system modules so that people interested in supporting a new language and creating new voices for MARY TTS can do so. The toolkit h...
متن کاملDevelopment of multi - voice and multi - language Text - to - Speech ( TTS ) and Speech - to - Text ( STT ) conversion system ( languages : Belorussian , Polish , Russian )
This proposal was submitted to INTAS Thematic Call on Information Technology 2004. The participants from 4 countries (Belarus, Poland, Russia and Germany) give efforts to the activity. The overall coordination, monitoring and control of the project will be implemented by Project Coordinator: Prof. Dr. Ruediger Hoffman (Team 1, IAS TUD, Germany) and Decision Board: Prof. Dr. Ruediger Hoffmann (T...
متن کاملConsiderations in the usage of text to speech (TTS) in the creation of natural sounding voice enabled web systems
The voice enabled web is a combination of XML based markup languages, speech recognition, text to speech (TTS) and web technologies. Key to the success of voice enabled web applications is the “naturalness” of the interface. Users are much more likely to interact with a system they feel comfortable with and that responds in a human like way. This paper describes the deployment of TTS in commerc...
متن کاملTBT (Toolkit to Build TTS): A High Performance Framework to Build Multiple Language HTS Voice
With the development of high quality TTS systems, application area of synthetic speech is increasing rapidly. Beyond the communication aids for the visually impaired and vocally handicap, TTS voices are being used in various educational, telecommunication and multimedia applications. All around the world people are trying to build TTS voice for their regional languages. TTS voice building requi...
متن کاملExpressive speech synthesis in MARY TTS using audiobook data and emotionML
This paper describes a framework for synthesis of expressive speech based on MARY TTS and Emotion Markup Language (EmotionML). We describe the creation of expressive unit selection and HMM-based voices using audiobook data labelled according to voice styles. Audiobook data is labelled/split according to voice styles by principal component analysis (PCA) of acoustic features extracted from segme...
متن کامل