Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Fu, Changzeng"'
I Know Your Feelings Before You Do: Predicting Future Affective Reactions in Human-Computer Dialogue
Autor:
Li, Yuanchao, Inoue, Koji, Tian, Leimin, Fu, Changzeng, Ishi, Carlos, Ishiguro, Hiroshi, Kawahara, Tatsuya, Lai, Catherine
Current Spoken Dialogue Systems (SDSs) often serve as passive listeners that respond only after receiving user speech. To achieve human-like dialogue, we propose a novel future prediction architecture that allows an SDS to anticipate future affective
Externí odkaz:
http://arxiv.org/abs/2303.00146
Autor:
Fu, Changzeng, Su, Yikai, Su, Kaifeng, Liu, Yinghao, Shi, Jiaqi, Wu, Bowen, Liu, Chaoran, Ishi, Carlos Toshinori, Ishiguro, Hiroshi
Publikováno v:
In Expert Systems With Applications 1 February 2025 261
Autor:
Fu, Changzeng, Qian, Fengkui, Su, Kaifeng, Su, Yikai, Wang, Ze, Shi, Jiaqi, Liu, Zhigang, Liu, Chaoran, Ishi, Carlos Toshinori
Publikováno v:
In Neural Networks January 2025 181
In this study, we explore the transformer's ability to capture intra-relations among frames by augmenting the receptive field of models. Concretely, we propose a CycleGAN-based model with the transformer and investigate its ability in the emotional v
Externí odkaz:
http://arxiv.org/abs/2111.15159
Publikováno v:
In Knowledge-Based Systems 3 August 2024 297
Autor:
Zhao, Yuliang, Liu, Yinghao, Li, Jian, Wang, Xiaoai, Yang, Ruige, Lian, Chao, Shan, Peng, Wang, Yulin, Zhan, Zhikun, Fu, Changzeng
Publikováno v:
In Expert Systems With Applications 1 June 2024 243
Autor:
Fu, Changzeng
We conducted a labeling work on a spoken Japanese dataset (I-JAS) for the text classification, which contains 50 interview dialogues of two-way Japanese conversation that discuss the participants' past present and future. Each dialogue is 30 minutes
Externí odkaz:
http://arxiv.org/abs/2103.11786
Text categorization is the task of assigning labels to documents written in a natural language, and it has numerous real-world applications including sentiment analysis as well as traditional topic assignment tasks. In this paper, we propose 5 differ
Externí odkaz:
http://arxiv.org/abs/2003.01857
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.