Junichi Yamagishi
Papers
1
Total Citations
34
H-Index
1
About
Junichi Yamagishi is a leading figure in speech processing, renowned for his pioneering work in speech synthesis, voice conversion, and speaker recognition. His research has fundamentally advanced the naturalness and emotional expressiveness of synthetic voices, particularly through the development of high-quality HMM-based and deep learning methods. A standout contribution is his work on "emotion transplantation," where he demonstrated how emotional characteristics could be transferred between speakers via adaptation in HMM-based speech synthesis—a paper that has garnered 34 citations and laid groundwork for expressive voice cloning. Yamagishi’s impact is profound, with his most-cited papers collectively amassing thousands of citations, reflecting his role in shaping modern text-to-speech and anti-spoofing technologies. He is also a key contributor to the ASVspoof challenge, which benchmarks voice authentication security. His achievements include receiving the prestigious ISCA Award for Best Paper and leading major international collaborations. For students and researchers, Yamagishi’s work exemplifies how rigorous engineering can unlock human-like emotion in machines, making him a vital reference in both academic and industrial speech AI.
Research Focus
Key Achievements
Top Papers
- 1Emotion transplantation through adaptation in HMM-based speech synthesis34 citations · 2015