Multilingual Text-To-Speech is a speech synthesis system that generates naturalistic spoken output in multiple languages from textual input, distinguished from monolingual counterparts by its ability to model cross-lingual prosodic, phonetic, and lexical variations within a unified framework.
211
Publications
8.6K
Citations
994
Authors
209
Institutions
Publications per year
2017–2026
100
Variants
Multilingual Tts
Parents
Publications
211
MLS: A Large-Scale Multilingual Dataset for Speech Research
Vineel Pratap, Qiantong Xu, Anuroop Sriram et al. · 2020 · 340 citations · Full text
Spanish Pre-trained BERT Model and Evaluation Data
José Cañete, Gabriel Chaperon, Rodrigo Fuentes et al. · arXiv (Cornell University) · 2023 · 337 citations · Full text
1–5 of 211
Authors
994
- TS
10
h-index
- JP
5
h-index
- JY
5
h-index
- AW
5
h-index
- CW
5
h-index
1–5 of 994
Institutions
209
Carnegie Mellon University
Pittsburgh, United States
12 h-index
41 publications
1.8K citations
Google (United States)
Mountain View, United States
9 h-index
40 publications
846 citations
University of Edinburgh
Edinburgh, United Kingdom
7 h-index
34 publications
1.4K citations
Karlsruhe Institute of Technology
Karlsruhe, Germany
5 h-index
33 publications
869 citations
Tsinghua University
Beijing, China
4 h-index
10 publications
173 citations
University of Zurich
Zurich, Switzerland
4 h-index
7 publications
284 citations
AT&T (United States)
Bedminster, United States
4 h-index
7 publications
207 citations
Johns Hopkins University
Baltimore, United States
4 h-index
12 publications
213 citations
1–8 of 209
Venues
- arXiv (Cornell University)
Repository · 14 publications · 635 citations
12
h-index
- International Conference on Acoustics, Speech, and Signal Processing
Conference · 4 publications · 174 citations
4
h-index
- Speech Communication
4 publications · 149 citations
4
h-index
- Machine Translation
3 publications · 77 citations
3
h-index
- Computer Speech & Language
3 publications · 599 citations
3
h-index
1–5