Constructing a Reusable Linguistic Resource for a Polyglot Speech Synthesis
نویسندگان
چکیده
This paper is about constructing sharable linguistic information to be used across languages for a Text-to-Speech (TTS) system. The data is obtained from existing resources. The focus of the paper is the phonetic and linguistic aspects. A monolingual TTS architecture is introduced with descriptions on each stage of processing. A multilingual TTS architecture is also introduced. Language dependent and language independent information required in the general TTS engine is described. Finally we will propose layer of communication between the pooled language information and a TTS engine in order to make it available for information reuse where possible for different languages.
منابع مشابه
Constructing a Multilingual Phoneme List for Polyglot Speech Synthesiser
We describe our approach to construct a phoneme set for polyglot speech synthesis. In polyglot speech synthesis, resources are shared across languages. The goal of this research is to develop global phoneme set using existing resources. Therefore, MBROLA has been selected. In MBROLA, there are 72 diphone databases of different languages. For each database, there is a set of phonemes used. We ha...
متن کاملPolyglot speech prosody control
Within a polyglot text-to-speech synthesis system, the generation of an adequate prosody for mixed-lingual texts, sentences, or even words, requires a polyglot prosody model that is able to seamlessly switch between languages and that applies the same voice for all languages. This paper presents the first polyglot prosody model that fulfills these requirements and that is constructed from indep...
متن کاملThe ESPRIT Project POLYGLOT
The ESPRIT project POLYGLOT aims at developing multi-lingual Speech-to-Text and Text-to-Speech conversion and to integrate this technology in a number of commercially viable prototype applications. Speech-to-Text conversion is mainly concerned with very large vocabulary isolated word recognition. It uses a statistical knowledge based approach that was pioneered for Italian and is now being exte...
متن کاملTime and space-efficient architecture for a corpus-based text-to-speech synthesis system
This paper proposes a time and space efficient architecture for a text-to-speech synthesis system (TTS). The proposed architecture can be efficiently used in those applications with unlimited domain, requiring multilingual or polyglot functionality. The integration of a queuing mechanism, heterogeneous graphs and finite-state machines gives a powerful, reliable and easily maintainable architect...
متن کاملBuilding Text-to-Speech Systems for Resource Poor Languages
The focus of this research is to develop a method for building Text to Speech Systems for resource poor languages by using data from other languages to fine tune a general template polyglot TTS architecture. Our method involves three main componants: language clustering, phoneme mappings and prosody modelling. As a proof of concept, four TTS have been implemented for English, Spanish, Malay and...
متن کامل