Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents最新文献

筛选

英文中文

Non-Native Speaker Generation and Perception for Mixed-Cultural Settings 混合文化背景下非母语人士的产生与感知

Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents Pub Date : 2019-07-01 DOI: 10.1145/3308532.3329427

David Obremski, Jean-Luc Lugrin, Philipp Schaper, Birgit Lugrin

引用次数: 7

An End-to-End Conversational Style Matching Agent 端到端会话风格匹配代理

Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents Pub Date : 2019-04-04 DOI: 10.1145/3308532.3329473

Rens Hoegen, Deepali Aneja, Daniel J. McDuff, M. Czerwinski

引用次数: 46

Analyzing Input and Output Representations for Speech-Driven Gesture Generation 语音驱动手势生成的输入输出表征分析

Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents Pub Date : 2019-03-08 DOI: 10.1145/3308532.3329472

Taras Kucherenko, Dai Hasegawa, G. Henter, Naoshi Kaneko, H. Kjellström

{"title":"Analyzing Input and Output Representations for Speech-Driven Gesture Generation","authors":"Taras Kucherenko, Dai Hasegawa, G. Henter, Naoshi Kaneko, H. Kjellström","doi":"10.1145/3308532.3329472","DOIUrl":"https://doi.org/10.1145/3308532.3329472","url":null,"abstract":"This paper presents a novel framework for automatic speech-driven gesture generation, applicable to human-agent interaction including both virtual agents and robots. Specifically, we extend recent deep-learning-based, data-driven methods for speech-driven gesture generation by incorporating representation learning. Our model takes speech as input and produces gestures as output, in the form of a sequence of 3D coordinates. Our approach consists of two steps. First, we learn a lower-dimensional representation of human motion using a denoising autoencoder neural network, consisting of a motion encoder MotionE and a motion decoder MotionD. The learned representation preserves the most important aspects of the human pose variation while removing less relevant variation. Second, we train a novel encoder network SpeechE to map from speech to a corresponding motion representation with reduced dimensionality. At test time, the speech encoder and the motion decoder networks are combined: SpeechE predicts motion representations based on a given speech signal and MotionD then decodes these representations to produce motion sequences. We evaluate different representation sizes in order to find the most effective dimensionality for the representation. We also evaluate the effects of using different speech features as input to the model. We find that mel-frequency cepstral coefficients (MFCCs), alone or combined with prosodic features, perform the best. The results of a subsequent user study confirm the benefits of the representation learning.","PeriodicalId":112642,"journal":{"name":"Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133074146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 112

首页上一页