Skip to Main content
Number of documents

4

Kévin Vythelingum


Research engineer

kevin (dot) vythelingum (at) voxygen (dot) fr

Voxygen
Route du Radôme
Pôle Phœnix Bat B1
22560 Pleumeur-Bodou
France

https://www.voxygen.fr

Bio

My main research interests are speech synthesis and speech recognition.

I have studied computer science (Master's degree) at the École Nationale Supérieure des Sciences Appliquées et de Technologie (Lannion, France) and the University of Rennes 1 (Rennes, France). I obtained my PhD in 2019, under the direction of Pr. Yannick Estève, at the Computer Science Lab (LIUM) of the University of Le Mans (Le Mans, France), in association with Voxygen.

I work since March 2016 with Voxygen as a research engineer. My current research activities focus on neural text-to-speech synthesis.


Yannick Estève   

Conference papers4 documents

  • Kévin Vythelingum, Yannick Estève, Olivier Rosec. Transcription phonétique automatique pour la synthèse de la parole. XXXIIe Journées d'Etudes sur la Parole (JEP 2018), Jun 2018, Aix-en-Provence, France. ⟨hal-01761937⟩
  • Kévin Vythelingum, Yannick Estève, Olivier Rosec. Acoustic-dependent Phonemic Transcription for Text-to-speech Synthesis. Interspeech 2018, Sep 2018, Hyderabad, India. ⟨10.21437/Interspeech.2018-1306⟩. ⟨hal-01870866⟩
  • Kévin Vythelingum, Yannick Estève, Olivier Rosec. Error detection of grapheme-to-phoneme conversion in text-to-speech synthesis using speech signal and lexical context. 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Dec 2017, Okinawa, Japan. ⟨10.1109/ASRU.2017.8269004⟩. ⟨hal-01585770⟩
  • Natalia Tomashenko, Kévin Vythelingum, Anthony Rousseau, Yannick Estève. LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic Challenge. IEEE Workshop on Spoken Language Technology, Dec 2016, San Diego, CA, USA, United States. ⟨10.1109/SLT.2016.7846278⟩. ⟨hal-01433188⟩