Diphone Synthesis is a speech synthesis method that concatenates diphones—minimal units of speech spanning the transition between adjacent phonemes—to generate continuous utterances with reduced prosodic artifacts compared to simpler concatenative approaches.
59
Publications
3K
Citations
131
Authors
38
Institutions
Publications per year
2017–2026
2
Parents
Publications
59
1–5 of 59
Authors
131
- EK
5
h-index
- JT
4
h-index
- AK
4
h-index
- ML
4
h-index
- AC
4
h-index
1–5 of 131
Institutions
38
AT&T (United States)
Bedminster, United States
4 h-index
12 publications
1.2K citations
Carnegie Mellon University
Pittsburgh, United States
3 h-index
4 publications
258 citations
Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
Orsay, France
3 h-index
5 publications
200 citations
Oregon Health & Science University
Portland, United States
3 h-index
11 publications
1.3K citations
University of Illinois Urbana-Champaign
Urbana, United States
2 h-index
6 publications
196 citations
International Institute of Information Technology, Hyderabad
Hyderabad, India
2 h-index
5 publications
226 citations
German Research Centre for Artificial Intelligence
Kaiserslautern, Germany
2 h-index
2 publications
80 citations
Saarland University
Saarbrücken, Germany
2 h-index
6 publications
224 citations
1–8 of 38
Venues
- The Journal of the Acoustical Society of America
JASA · 4 publications · 276 citations
4
h-index
- Publications of the UdS (Saarland University)
Repository · 3 publications · 89 citations
3
h-index
- The Journal of the Abraham Lincoln Association
2 publications · 39 citations
2
h-index
- International Conference on Acoustics, Speech, and Signal Processing
Conference · 2 publications · 157 citations
2
h-index
- IEEE Transactions on Audio Speech and Language Processing
1 publications · 13 citations
1
h-index
1–5