Japanese Page / English Page
TOKUDA and NANKAKU LABORATORY
For Local Only
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

  • No information.

News

August 30, 2017 IEICE ISS Young Researcher's Award in Speech Field

award.png

August 30, 2017
Kei Hashimoto (Associate Prof) received the 2016 IEICE ISS Young Researcher's Award in Speech Field.
Congratulations!

by Fumiyoshi Ikeura

August 25, 2017 Blizzard Challenge 2017 Workshop

August 25, 2017
Blizzard Challenge 2017 Workshop was held in Stockholm (Sweden).

Organizer, Session Chair

  • Keiichi Tokuda (Prof)

Presenter

  • Kei Sawada (D3)

by Fumiyoshi Ikeura

August 20, 2017 Interspeech 2017

August 20, 2017 (5days)
Interspeech2017 was held in Stockholm (Sweden).

Participants

  • Keiichi Tokuda (Prof)
  • Kei Sawada (D3)

by Fumiyoshi Ikeura

August 10, 2017 Farewell Luncheon for Alexander

20170810_1.jpg 20170810_2.jpg 20170810_3.jpg

August 10, 2017
We held a farewell lunch party for Alexander at Cafe House LIEBE.
We enjoyed Miso cutlets specialized in Nagoya and had a good time.

by Fumiyoshi Ikeura

August 04, 2017 Extension lecture

20170804_1.jpg 20170804_2.jpg 20170804_3.jpg

August 04, 2017
The extension lecture(Japanese only) was held at Nagoya Institute of Technology.
This time, we performed some demonstrations of the research that has been conducted in our lab and Lee & Sako lab. The following topics were presented.

  • Speech Analysis
  • Speech Synthesis
    • Emotional Speech Synthesis (Open JTalk)
    • Singing Voice Synthesis (Sinsy)
    • HAL-O-ROID (CeVIO)
  • Speech Recognition
    • Large Vocabulary Continuous Speech Recognition (Julius)
    • Speaker Recognition
  • Image Recognition
    • bimodal Speech Recognition
  • Spoken Dialog System
    • Voice-Interactive Digital Signage (MMDAgent,Galatea)
  • Music information processing

Many people participated regardless of generations.
Through the demonstration, I'm pleased if the knowledge on media information technology expands.

by Fumiyoshi Ikeura

August 03, 2017 The 2017 N.I.T's open campus

20170803_1.jpg 20170803_2.jpg 20170803_3.jpg

August 03, 2017
The 2017 2nd open campus was held at Nagoya Institute of Technology.
This time, we performed some demonstrations of the research that has been conducted in our lab and Lee & Sako lab. The following topics were presented.

  • Speech Synthesis
    • Emotional Speech Synthesis (Open JTalk)
    • Singing Voice Synthesis (Sinsy)
    • HAL-O-ROID (CeVIO)
  • Speech Recognition
    • Large Vocabulary Continuous Speech Recognition (Julius)
    • Speaker Recognition
  • Spoken Dialog System
    • Voice-Interactive Digital Signage (MMDAgent)
  • Music information processing

Many high school students came to watch our demos.
It would be grateful for us to know they got interested in information engineering from watching them.

by Natsumi Koike

July 31, 2017 The comment presented at TV show

July 31, 2017
Professor Keiichi Tokuda's comment on recent speech synthesis technology was introduced in NEWS Shibu5(Japanese only).

Broadcast : July 31 (Mon.) 16:50 ~ 18:10 (NHK)

by Fumiyoshi Ikeura

> Events archive

トップ   編集 凍結 差分 バックアップ 添付 複製 名前変更 リロード   新規 一覧 単語検索 最終更新   ヘルプ   最終更新のRSS