About Our Laboratory

We are working on speech information processing with a focus on speech recognition.

Announce

2018.3
Innovative Asia (Master's program with scholarship for some Asian countries) is announced by JICA. To apply for our lab, contact Takahiro Shinozaki well in advance of the application deadline.

What's new

2018.6
A student from The Hong Kong University of Science and Technology is visiting for a summer program.
2018.1
A paper by a master student is accepted for IEEE ICASSP 2018.
2017.12
An undergraduate student gave a presentation at IEEE ASRU.
2017.12
A master student gave a presentation at IWSLT.
2017.12
Research students Bairong et al. published their work on DSTC6.
2017.11
Hosted a student from The University of Melbourne as a winter program. She worked on machine translation. (2017.11-2018.2)
2017.6,7
Panida Wiriyachaiporn and Sirawit Onpraphai from Thailand stayed our lab for two months as visiting students. Panida (Chulalongkorn University) worked on a Thai singing-voice speech synthesis system, Sirawit (Chiang Mai University) worked on an end-to-end speech recognition system.
2017.3
Tomohiro Tanaka, a master student, received an excellent student presentation award from the Acoustic Society of Japan.
2016.10
Uploaded slides for invited talk at SP October meeting. (CSJ recipe for Kaldi)
2016.10
Uploaded slides for invited talk at GTC2016 conference. (Evolutionary optimization of ASR systems)
2016.10
Tomohiro Tanaka, a master student, received an excellent student presentation award from the Acoustic Society of Japan.
2016.9
Uploaded speech recognition lecture slides
2016.8
Gave a lecture in a seminar held at Kyoto University
2016.7
Attended Frederick Jelinex Memorial Summer Workshop
photo1photo2
2016.5
Updated Kaldi CSJ recipe.
2016.4
Uploaded LSTM-LM meta-prameters optimized by evolutionary computation peformed on Tsubame super computer.
2016.4
Remodeled the homepage following the education reform of Tokyo Tech.
2016.3
Takafumi Moriya, a master student, received an excellent student presentation award from the Acoustic Society of Japan.
2016.2
Tutorial materials for the Kaldi CSJ recipe is available (in Japanese).
2015.11
Our proposal has been accepted for 2016 Jelinek Summer Workshop in Speech and Language Technology.
2015.5.16
A Kaldi based recipe is released for Japanese large vocabulary spontaneous speech recognition using the Corpus of Spontaneous Japanese (CSJ). The recipe is developed by a cooperation of our lab and Mitsubishi Electric Research Lab in the US. It is included in the official Kaldi package under egs/csj.

history