Tokuda, Lee and Nankaku laboratory develops research on speech signal processing and multimedia signal processing including speech synthesis, singing voice synthesis, speech recognition and spoken dialog systems development.
Information
News
May 05, 2018 Farewell Party for Prof. Thomas Hain
May 02, 2018
We held a farewell party for Prof. Thomas Hain
(The University of Sheffield).
Thank you, Prof. Thomas Hain.
by Kento Nakao
April 27, 2018 Monthly Party
April 27, 2018
We had our April's monthly party.
It was also a welcome party for the new 4th year bachelor students, who just entered the lab. So, they made a quick self-introduction speech to the others.
Let's all give our best for this year!
by Yasumasa Kojima
April 26, 2018 Publication
April 26, 2018
The following paper was published in IEEE/ACM Transactions on Audio, Speech and Language Processing:
"Mel-Cepstrum-Based Quantization Noise Shaping Applied to Neural-Network-Based Speech Waveform Synthesis"
by Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
by Kento Nakao
April 15, 2018 ICASSP2018
April 15, 2018 (5days)
ICASSP2018 was held in Calgary (Canada).
We thank participants for all the hard work.
Presenters
- Jumpei Niwa (M2)
- Eiji Ichikawa (M2)
Participants
- Kei Hashimoto (Associate Prof)
by Yasumasa Kojima
April 06, 2018 A meeting with Dr. Heiga Zen
April 06, 2018
Heiga Zen (OB, Google) visited Nagoya Institute of Technology and held a meeting with students.
Listening to his valuable story has become very helpful to us.
by Yasumasa Kojima
April 04, 2018 Professor Thomas Hain's Talk
April 04, 2018
A lecture was held by the professor Thomas Hain.
It was a lecture on speech recognition and it was a great learning experience.
by Kento Nakao
March 30, 2018 the 2017 IEEE Nagoya Section Excellent student Award
March 30, 2018
Jumpei Niwa (M1) and Eiji Ichikawa (M1) received the 2017 IEEE Nagoya Section Excellent student Award.
Congratulations!
by Yasumasa Kojima
> Events archive
