Français
5. Acoustic synthesis
Once the text to be produced has been analyzed, the next step is acoustic synthesis, which involves transforming the sequence of symbols obtained during linguistic analysis into a sequence of signal samples. There are two main classes of acoustic synthesis techniques: parametric and non-parametric.
In parametric synthesis, the signal is calculated using a model of the speech signal, the source-filter model: the signal passes through a "vocoder" (for "voice coder", or analysis-synthesis system).
In non-parametric synthesis, signal samples are concatenated with minimal modifications, without the need for a vocoder.
5.1 Rule-based formant synthesis
The rule-based synthesizer calculates the evolution (trajectories)...
The Ultimate Scientific and Technical Reference
This article is included in
Digital documents and content management
This offer includes:
Knowledge Base
Updated and enriched with articles validated by our scientific committees
Services
A set of exclusive tools to complement the resources
Practical Path
Operational and didactic, to guarantee the acquisition of transversal skills
Doc & Quiz
Interactive articles with quizzes, for constructive reading
Acoustic synthesis
Speech synthesis applications
Bibliography
- (1) - SPROAT (R.), MOEBIUS (B.), MAEDA (K.), TZOUKERMANN (E.) - Multilingual text analysis. - Dans Multilingual Text-To-Speech Synthesis – The Bell Labs Approach, SPROAT (R.) et coll. éd., Kluwer Academic Publishers (1998). Ce livre décrit en détail les procédures de synthèse de l'anglais et d'autres langues, et donne une introduction au...
Commercial data
-
Acapela http://www.acapela-group.com/
Acapela is the new name of the group formed by BaBel Technologies SA and Babel-Infovox AB, which also absorbed ELAN speech. Acapela offers a wide range of multilingual synthesis solutions, initially developed through research at the Royal Institute of Technology...
Magazines, conferences
Recent developments in the techniques presented here are regularly the subject of articles.
In journals devoted to speech processing:
• IEEE Transactions on Speech and Audio Processing ;
• Speech Communication ;
• Computer Speech and Language ;
• EURASIP Journal...
The Ultimate Scientific and Technical Reference
