Skip to main content
European Commission logo print header
Zawartość zarchiwizowana w dniu 2022-11-15

Voices, Attitudes and Emotions in Speech Synthesis

Cel

The VAESS project involves the development of a communication aid, improved quality and range of synthetic voices in four languages, and automatic speech labelling.

This project will develop a fully portable (hand-held) communicator with versatile, high quality speech output. By combining the latest advances in speech technology with state-of-the-art hardware we will extend the capabilities of current speech prostheses.

Currently the use of speech synthesis based communication aids is adversely affected by their inappropriate and artificial voices, and by limited ability to express emotion efficiently. Provision of a genuinely personalised voice would be a major advantage over current aids.

The methods developed will be tested by implementing male, female, and if time permits, children's voices. An attempt will be made to include a range of attitudes and emotions in the synthesised speech, and to provide efficient user control of these features.

Although the initial aim of the project is to produce a flexible speech communication aid for disabled people, the techniques developed would also have significant potential for exploitation in devices for non-disabled users. In particular, multi-media and home entertainment systems would benefit from more varied vocal styles, or even ones which could be modified by the users.

Other potential aids for disabled people would include 'talking newspapers' and electronic messaging systems (E-mail) with voices customisable by the user to increase intelligibility and reduce 'listening fatigue'.

Overall, the structure of the project will include the following steps:

1) Study and manual labelling of speech features for voices, attitudes and emotion.
2) Development of automatic or semi-automatic labelling of above and conversion into text-to-speech control parameters.
3) Hardware platform development for operation with and without DSP.
4) Development of the user interface.
5) Integration of the systems.
6) User evaluation of the systems and completion of the user interface.

The present Infovox synthesis technology, available for some ten European languages, will be augmented and generalised to enable use in a variety of present and future devices for elderly and disabled people.

All the deliverables from this project have the potential for commercial exploitation. The combination of the Infovox speech technology and the small portable PC based BiDesign platform will offer very strong competition to current European and non-European systems alike. The availability of such systems for two of the most widely used languages world-wide (English and Spanish) should make subsequent exploitation highly profitable.

One area in which it is aimed to establish measurable improvements over existing 'technologies' is in automatic speech labelling. The aim will be to at least halve the error rate in the automatic speech labelling process.

Zaproszenie do składania wniosków

Data not available

System finansowania

CSC - Cost-sharing contracts

Koordynator

University of Sheffield
Wkład UE
Brak danych
Adres
Mappin Street
S1 3JD Sheffield
Zjednoczone Królestwo

Zobacz na mapie

Koszt całkowity
Brak danych

Uczestnicy (6)