Home HomeABSTRACT
Most English text-to-speech synthesisers offer one of only two accents: General American or RP. Developing a new accent is laborious, since it is not possible to choose one accent as a base form and systematically translate to others. We use the approach of Wells ([1]), categorising vowels in terms of abstract keywords that encode classes of words. Thus it is unnecessary to use a phonemic transcription in either the development or the execution of a synthesiser. The "keyvowel" system can be used throughout the synthesis system, avoiding the need to make accent-specific changes manually. The same linguistic resources can be re-used for each new accent. More fundamentally, the keyvowel system functions as a meta-accent that subsumes vowel-related information in all accents of English.
A0013.pdf
TOPABSTRACT
The LPC-MPE synthesis method is an alternative method used for obtaining a better quality of the generated vocal signal, that can be easily implemented in vocal signal coding-decoding systems. Using the method in text-to-speech systems is more difficult because of the modification that must be done on the synthesized vocal signal in order to superimpose prosodical effects. This paper presents our steps in this direction, some researches and experimental results obtained for adapting the system to the pitch-synchronous LPC-MPE method.
A0449.pdf
TOPABSTRACT
In this paper we present an overview of the German version of the Bell Labs text-to-speech system, a high-quality concatenative synthesis system with extensive text analysis capabilities. We discuss problems of text analysis, and our solutions to these problems, including: the integration of text normalization tasks into linguistic text analysis; the capability to morphologically analyze compounds and unseen words; name analysis and pronunciation. We briefly describe the prosodic components of the text-to-speech system and their underlying duration and intonation models. Finally, the phonetically motivated structure of the acoustic inventory is presented.
A0479.pdf
TOPABSTRACT
Most speech synthesisers and recognisers for English currently use pronunciation lexicons in standard British or American accents, but as use of speech technology grows there will be more demand for the incorporation of regional accents. This paper describes the use of rules to transform existing lexicons of standard British and American pronunciations to a set of regional British and American accents. The paper briefly discusses some features describes of the regional accents in the project, and the framework used for generating pronunciations. Certain theoretical and practical problems are highlighted; for some of these, solutions are suggested, but it is shown that some difficulties cannot be resolved by automatic rules. However, although the method described cannot produce phonetic transcriptions with 100% accuracy, it is more accurate than using letter-to-sound rules, and faster than producing transcriptions by hand.
A0793.pdf
TOPABSTRACT
This paper describes the Bell Labs Russian text-to-speech system, a concatenative system with extensive text-analysis capabilities. The construction of Russian-specific modules will be discussed, including the text-analysis module, the acoustic inventory, the duration module, and the intonation module.
A0919.pdf
TOPABSTRACT
This paper summarises the text-to-speech system that has been developed during the last years in the Speech Group of the Universitat Politècnica de Catalunya (UPC). The paper emphasises the parts of the system which are language dependent: phonetic transcription, prosodic module, and synthesis units database. One particularity of the system is the fact of being bilingual, i.e., the system is able to speak either in Spanish or in Catalan. Some effort has been done to allow the reading of bilingual texts and to reduce the computational resources needed. In particular, the Spanish and Catalan speech databases are merged to reduce the memory requirements and the development effort. The system is being used by disabled people which suffer from oral disorders. In order to give variability to the voices some experiments have been done in voice transformation using the TD-PSOLA algorithm.
A1283.pdf
TOP
Recordings