Papers - LEE Akinobu
-
発話交替頻度を導入した実対話音声に対するSpeaker Diarizationのためのデータ生成
市川 奎吾, 上乃 聖, 李晃伸
日本音響学会講演論文集 2023.09
Authorship：Last author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
CGアバター対話における音声からの頭部動作および表情の自動生成
藤岡 侑貴, 上乃 聖, 李晃伸
人工知能学会全国大会 2023.06
Authorship：Last author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
複数設定のスペクトログラムを用いた音声合成に基づく音声認識のデータ拡張
上乃聖, 李晃伸
日本音響学会講演論文集 2023.03
Authorship：Last author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Continuous Integrate-and-Fire を用いた音声区間検出とターン終了検知のマルチタスク学習
池口 弘尚, 東 佑樹, 上乃 聖，李 晃伸
日本音響学会講演論文集 2023.03
Authorship：Last author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
連続的な感情表出を用いたカウンセリング対話エージェントの評価
川又 朱莉, 上乃 聖, 李 晃伸
HAIシンポジウム 2023.03
Authorship：Last author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
多様な笑い声生成のための有声音・無声音間隔の制御
木全亮太朗, 上乃 聖, 李 晃伸
情報処理学会全国大会講演論文集 2023.03
Authorship：Last author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
自律・遠隔融合対話システムのための高生命感・高存在感CGエージェントの開発
李晃伸, 石黒浩
第96回 人工知能学会 言語・音声理解と対話処理研究会（第13回対話システムシンポジウム） 2022.12
Authorship：Lead author, Corresponding author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
自己投影アバターによる引き込みを用いた2D-CG音声対話システム
東省吾, 李晃伸
ヒューマンインタフェースシンポジウム2022 2T-P2 2022.09
Authorship：Last author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
音声認識のデータ拡張のための話者情報およびマスクを用いた合成音声の周波数スペクトログラム強調
上乃 聖，李 晃伸，河原 達也
日本音響学会講演論文集 1149 - 1150 2022.09
Language：Japanese Publishing type：Research paper (other academic)
-
自動音声対話におけるネガティブ感情認識のための転移学習の性能比較
高井幸輝, 李晃伸, 戸田隆道, 東佑樹, 下山翔
人工知能学会 言語・音声理解と対話処理研究会（SLUD）第93回研究会 2021.11
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
自動音声応答におけるユーザー沈黙時の発話誘導
西山達也, 李晃伸, 戸田隆道, 友松祐太, 杉山雅和
人工知能学会 言語・音声理解と対話処理研究会（SLUD）第90回研究会 2020.11
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Context and Knowledge Aware Dialogue System and System Combination for Grounded Response Generation Reviewed International coauthorship International journal
Ryota Tanaka, Akihide Ozeki, Shugo Kato, Akinobu Lee
Computer Speech & Language 62 2020.07
Language：English Publishing type：Research paper (scientific journal) Publisher：Elsevier
DOI： 10.1016/j.csl.2020.101070
Other Link： https://www.sciencedirect.com/science/article/pii/S0885230820300036
-
Fact-based Dialogue Generation with Convergent and Divergent Decoding International journal
Ryota Tanaka, Akinobu Lee
arXiv 2020.05
Language：English Publishing type：Research paper (other academic)
Fact-based dialogue generation is a task of generating a human-like response based on both dialogue context and factual texts. Various methods were proposed to focus on generating informative words that contain facts effectively. However, previous works implicitly assume a topic to be kept on a dialogue and usually converse passively, therefore the systems have a difficulty to generate diverse responses that provide meaningful information proactively. This paper proposes an end-to-end fact-based dialogue system augmented with the ability of convergent and divergent thinking over both context and facts, which can converse about the current topic or introduce a new topic. Specifically, our model incorporates a novel convergent and divergent decoding that can generate informative and diverse responses considering not only given inputs (context and facts) but also inputs-related topics. Both automatic and human evaluation results on DSTC7 dataset show that our model significantly outperforms state-of-the-art baselines, indicating that our model can generate more appropriate, informative, and diverse responses.
-
Speaker-Aware BERT for Multi-Party Dialog Response Selection Reviewed International coauthorship International journal
Tatsuya Nishiyama, Ryota Tanaka, Yuya Ishijima, Akinobu Lee
Proc. AAAI2020 Dialogue System Technology Challenge 8 workshop 2020.02
Language：English Publishing type：Research paper (international conference proceedings)
Other Link： https://sites.google.com/dstc.community/dstc8/aaai-20-workshop
-
言語対の音素事後確率を用いた第二言語学習者の発音習熟度判別
森凜太朗, 李晃伸
電子情報通信学会 音声研究会（IEICE-SP） 2019.12
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
個別の発話スタイルを強調する Boosting Framework を用いた感情表現生成
尾関晃英, 李晃伸
情報処理学会 自然言語処理研究会（IPSJ-NL） 2019.12
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
話題展開器を導入した外部知識に基づくニューラル対話モデル
田中涼太, 李晃伸
情報処理学会 自然言語処理研究会（IPSJ-NL） 2019.12
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Ensemble Dialogue System for Facts-Based Sentence Generation Reviewed International coauthorship International journal
Ryota Tanaka, Akihide Ozeki, Shugo Kato, Akinobu Lee
Proc. AAAI2019 Dialogue System Technology Challenge 7 workshop 2019.01
Language：English Publishing type：Research paper (international conference proceedings)
Other Link： http://workshop.colips.org/dstc7/workshop.html
-
Machine Learning and Language Learning: English Conversation Simulator and its Design for Language Learning Reviewed
KIMURA Mitsushige, LEE Akinobu, KAWASHIMA Hiroaki
Journal of The Society of Instrument and Control Engineers 58 ( 11 ) 873 - 877 2019
Language：Japanese Publishing type：Research paper (scientific journal) Publisher：The Society of Instrument and Control Engineers
-
外部事実情報と対話履歴を用いたアンサンブル対話システム
田中涼太, 尾関晃英, 加藤修悟, 李晃伸
SIG-SLUD 2018.11
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
This study aims to avoid "safe response" by conditioning context and external facts
extracted from information websites (e.g. Wikipedia), and then generate the response based on
real-world facts. This system consists of the three sub modules i.e. Ensemble Dialogue System,
where generated-based module, facts retrieval module, and reranking module. Thus, the response
can be determined from various viewpoints by combining multiple systems. The experiments
and evaluations are conducted based on sentence generation task of Dialog System Technology
Challenges 7, and then our system performed significantly better than many competing systems.
