At the 153rd (Spring 2025) Research Presentation of the Acoustical Society of Japan, held from March 17 to March 19, Keigo Ichikawa (M2), Momone Suzuki (B4), and Professor Sei Ueno gave presentations on the following topics.
「話者遷移確率に基づく話者ダイアライゼーションのためのデータ生成」 Keigo Ichikawa，Sei Ueno，Akinobu Lee 「音響情報を考慮した大規模言語モデルによる音声認識の誤り訂正」 Momone Suzuki，Sei Ueno，Akinobu Lee
「拡散モデルを用いた音声合成による音声認識のデータ拡張」 Sei Ueno，Akinobu Lee
At the 31st Annual Meeting of the Association for Natural Language Processing (NLP2025), held from March 10 to March 14, B4 student Yukito Minari gave a presentation on the following topic.
「LLM ベースのマルチエージェントによる TRPG ゲームマスターシステムの実現」 Yukito Minari，Sei Ueno，Akinobu Lee
At the HAI Symposium 2025, held from February 28 to March 1, M2 students Akari Kawamata and Yuki Fujioka, as well as B4 students Soma Suzuki, Takumi Yoshida, and Koki Yamada, presented on the following topics.
「身体性を持つCG対話エージェントにおけるカートゥーン調表現の方法論および比較評価」 Akari Kawamata, Sei Ueno，Akinobu Lee(Nagoya Institute of Technology)
「CGアバター遠隔対話のための音声からのモーション生成およびCG特有性の分析」 Yuki Fujioka, Sei Ueno，Akinobu Lee
「アバター会話支援のための音声からのリアルタイム会話モーション生成の検討」 Soma Suzuki, Sei Ueno，Akinobu Lee
「医療面接教育のための仮想模擬患者を用いた没入型音声対話システム」 Takumi Yoshida, Sei Ueno，Akinobu Lee
「CGエージェントを用いた対話システムにおける疑似ソーシャルタッチの効果」 Koki Yamada, Sei Ueno，Akinobu Lee
At the 2024 master’s degree interim presentation, M2 students Akari Kawamata and Ryotaro Kimata won the Best Presentation Award, The Tokai Chapter of Acoustical Society of Japan（日本音響学会東海支部優秀発表賞）.
Keigo Ichikawa (M2) made a presentation at the Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2024) held on December 3rd to 6th.
“Data generation for speaker diarization by speaker transition information” Keigo Ichikawa, Sei Ueno, and Akinobu Lee
Ryota Tanaka (M2)’s paper has been published at Computer Speech & Language jounal.
Ryota Tanaka, Akihide Ozeki, Shugo Kato, Akinobu Lee, “Context and Knowledge Aware Dialogue System and System Combination for Grounded Response Generation” In Proc. Computer Speech & Language Journal, vol. 62, July 2020. http://www.sciencedirect.com/science/article/pii/S0885230820300036
A paper entitled “Speaker Aware BERT for Multi-Party Dialogue Selection” by Tatsuya Nishiyama has been accepted for poster presentation at AAAI2020/DSTC8, which will be held on New York on February 8, 2020.
