1 code implementation • 28 May 2023 • Sewade Ogun, Vincent Colotte, Emmanuel Vincent
Flow-based generative models are widely used in text-to-speech (TTS) systems to learn the distribution of audio features (e. g., Mel-spectrograms) given the input tokens and to sample from this distribution to generate diverse utterances.
1 code implementation • 12 Oct 2022 • Sewade Ogun, Vincent Colotte, Emmanuel Vincent
We show the viability of this approach for training a multi-speaker GlowTTS model on the Common Voice English dataset.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • JEPTALNRECITAL 2020 • Sara Dahmani, Vincent Colotte, Slim Ouni
Dans le pass{\'e}, les descripteurs contextuels pour la synth{\`e}se de la parole acoustique ont {\'e}t{\'e} {\'e}tudi{\'e}s pour l{'}entra{\^\i}nement des syst{\`e}mes bas{\'e}s sur des HMMs.
no code implementations • LREC 2016 • Juergen Trouvain, Anne Bonneau, Vincent Colotte, Camille Fauth, Dominique Fohr, Denis Jouvet, Jeanin J{\"u}gler, Yves Laprie, Odile Mella, Bernd M{\"o}bius, Frank Zimmerer
The IFCASL corpus is a French-German bilingual phonetic learner corpus designed, recorded and annotated in a project on individualized feedback in computer-assisted spoken language learning.
no code implementations • LREC 2014 • Camille Fauth, Anne Bonneau, Frank Zimmerer, Juergen Trouvain, Bistra Andreeva, Vincent Colotte, Dominique Fohr, Denis Jouvet, Jeanin J{\"u}gler, Yves Laprie, Odile Mella, Bernd M{\"o}bius
We present the design of a corpus of native and non-native speech for the language pair French-German, with a special emphasis on phonetic and prosodic aspects.