Scholar
Nicolas Obin
Google Scholar ID: 1V4gWyEAAAAJ
Associate professor -- Ircam, Sorbonne Université
Speech Synthesis
Voice Conversion
Generative Audio
Creative Generation
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
602
H-index
13
i10-index
21
Publications
20
Co-authors
25
list available
Publications
7 items
A Comprehensive Study of Content Representations for Speech Synthesis
2026
Cited
0
Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion
2026
Cited
0
PitchFlower: A flow-based neural audio codec with pitch controllability
2025
Cited
0
Gelina: Unified Speech and Gesture Synthesis via Interleaved Token Prediction
2025
Cited
0
Learning Relationships Between Separate Audio Tracks for Creative Applications
2025
Cited
0
Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters
2025
Cited
0
Lina-Speech: Gated Linear Attention is a Fast and Parameter-Efficient Learner for text-to-speech synthesis
arXiv.org · 2024
Cited
4
Co-authors
8 total
Axel Roebel
IRCAM (STMS Laboratory)
Jean-Philippe Goldman
University of Geneva
Sylvain Kahane
University Paris Nanterre, Modyco & CNRS / Institut Universitaire de France
Volker Dellwo
University of Zurich
Junichi Yamagishi
National Institute of Informatics, Tokyo, Japan
Roberto Barra-Chicote
Amazon Artificial General Intelligence (AGI)
Jaime Lorenzo-Trueba
Assembly AI
Xavier Serra
Department of Information and Communication Technologies, Universitat Pompeu Fabra (UPF), Barcelona
