知能コミュニケーション研究室のAndros Tjandraさん(博士後期課程3年)が、日本音響学会より学生優秀発表賞を受賞しました。
Andros Tjandra, a doctoral student of Augmented Human Communication lab., received a student excellence presentation award from the Acoustical Society of Japan.
(2019/3/6)
|
日本音響学会は、1936年の発足以来、「音」に関するあらゆる分野の研究者や技術者が多数参加しています。現在の会員数は4500名余で， 世界的にはアメリカ音響学会に次ぐ規模になっています。学会の活動は多岐に及び、学会誌の発行をはじめ、月例の研究会、春と秋の研究発表会、公開セミナー、シンポジウムの開催などを研究委員会が中心となり、定期的におこなっています。Andros Tjandraさんは2018年秋季研究発表会での講演が評価され、学生優秀発表賞が贈呈されました。贈呈式は、2019年3月6日の2019年春季研究発表会で執り行われました。 The 2018 Autumn meeting of the Acoustical Society of Japan was held from September 12 to September 14, 2018 at Oita University, Oita, Japan. Mr. Andros Tjandra's presentation at that meeting was awarded a student excellence presentation award in the 2019 Spring meeting. |
- 受賞者 Awardee:
Andros Tjandra
写真はAndros Tjandraさん
- 受賞テーマ Research theme:
"Machine Speech Chain with Deep Learning”
We develop a closed-loop speech chain model based on deep learning and construct a sequence-to-sequence model for both ASR and TTS tasks as well as a loop connection between these two processes. The sequence-to-sequence model in closed-loop architecture allows us to train our model on the concatenation of both labeled and unlabeled data. While ASR transcribes the unlabeled speech features, TTS attempts to reconstruct the original speech waveform based on text from ASR. In the opposite direction, ASR also reconstructs the original text transcription given the synthesized speech.
To the best of our knowledge, this is the first deep learning model that integrates human speech perception and production behaviors.
- 著者 Authors:
Andros Tjandra, Sakriani Sakti, Satoshi Nakamura
- 受賞者のコメント Awardee's voice
It's such a great honor to receive this award. I would like to express my gratitude to my supervisors and collaborators for their support and guidance. Furthermore, I hope this award will encourage me to create something even better in the future.
- 外部リンク Links to：
日本音響学会 HP:http://www.asj.gr.jp/index.html