{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T15:14:44Z","timestamp":1770909284891,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,27]],"date-time":"2017-10-27T00:00:00Z","timestamp":1509062400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,10,27]]},"DOI":"10.1145\/3125739.3132594","type":"proceedings-article","created":{"date-parts":[[2017,10,16]],"date-time":"2017-10-16T12:37:48Z","timestamp":1508157468000},"page":"365-369","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":35,"title":["Speech-to-Gesture Generation"],"prefix":"10.1145","author":[{"given":"Kenta","family":"Takeuchi","sequence":"first","affiliation":[{"name":"Aoyama Gakuin University, Sagamihara, Japan"}]},{"given":"Dai","family":"Hasegawa","sequence":"additional","affiliation":[{"name":"Aoyama Gakuin University, Sagamihara, Kanagawa, Japan"}]},{"given":"Shinichi","family":"Shirakawa","sequence":"additional","affiliation":[{"name":"Yokohama National University, Yokohama, Kanagawa, Japan"}]},{"given":"Naoshi","family":"Kaneko","sequence":"additional","affiliation":[{"name":"Aoyama Gakuin University, Sagamihara, Kanagawa, Japan"}]},{"given":"Hiroshi","family":"Sakuta","sequence":"additional","affiliation":[{"name":"Aoyama Gakuin University, Sagamihara, Kanagawa, Japan"}]},{"given":"Kazuhiko","family":"Sumi","sequence":"additional","affiliation":[{"name":"Aoyama Gakuin University, Sagamihara, Kanagawa, Japan"}]}],"member":"320","published-online":{"date-parts":[[2017,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"https:\/\/youtu.be\/MAs4iKGToBU https:\/\/youtu.be\/MAs4iKGToBU"},{"key":"e_1_3_2_1_2_1","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dan Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow:Large-Scale Machine Learning on Heterogeneous Systems. (2015). http:\/\/tensorflow.org\/ Software available from tensorflow.org. Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Greg S. Corrado Andy Davis Jeffrey Dean Matthieu Devin Sanjay Ghemawat Ian Goodfellow Andrew Harp Geoffrey Irving Michael Isard Yangqing Jia Rafal Jozefowicz Lukasz Kaiser Manjunath Kudlur Josh Levenberg Dan Man\u00e9 Rajat Monga Sherry Moore Derek Murray Chris Olah Mike Schuster Jonathon Shlens Benoit Steiner Ilya Sutskever Kunal Talwar Paul Tucker Vincent Vanhoucke Vijay Vasudevan Fernanda Vi\u00e9gas Oriol Vinyals Pete Warden Martin Wattenberg Martin Wicke Yuan Yu and Xiaoqiang Zheng. 2015. TensorFlow:Large-Scale Machine Learning on Heterogeneous Systems. (2015). http:\/\/tensorflow.org\/ Software available from tensorflow.org."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Justine Cassell Stefan Kopp Paul Tepper Kim Ferriman and Kristina Striegnitz. 2007. Trading spaces:How humans and humanoids use speech and gesture to give directions. Conversational informatics (2007) 133--160. Justine Cassell Stefan Kopp Paul Tepper Kim Ferriman and Kristina Striegnitz. 2007. Trading spaces:How humans and humanoids use speech and gesture to give directions. Conversational informatics (2007) 133--160.","DOI":"10.1002\/9780470512470.ch8"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383315"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23974-8_14"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21996-7_17"},{"key":"e_1_3_2_1_7_1","unstructured":"Fran\u00e7ois Chollet and others. 2015. Keras. https:\/\/github.com\/fchollet\/keras. (2015). Fran\u00e7ois Chollet and others. 2015. Keras. https:\/\/github.com\/fchollet\/keras. (2015)."},{"key":"e_1_3_2_1_8_1","unstructured":"Awni Hannun Carl Case Jared Casper Bryan Catanzaro Greg Diamos Erich Elsen Ryan Prenger Sanjeev Satheesh Shubho Sengupta Adam Coates and others. 2014. Deep speech:Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014). Awni Hannun Carl Case Jared Casper Bryan Catanzaro Greg Diamos Erich Elsen Ryan Prenger Sanjeev Satheesh Shubho Sengupta Adam Coates and others. 2014. Deep speech:Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Machine Learning. 448--456","author":"Ioffe Sergey","year":"2015"},{"key":"e_1_3_2_1_11_1","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam:A Method for Stochastic Optimization. CoRR abs\/1412.6980 (2014). http:\/\/arxiv.org\/abs\/1412.6980 Diederik P. Kingma and Jimmy Ba. 2014. Adam:A Method for Stochastic Optimization. CoRR abs\/1412.6980 (2014). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_12_1","unstructured":"David McNeill. 1992. Hand and mind:What gestures reveal about thought. University of Chicago press. David McNeill. 1992. Hand and mind:What gestures reveal about thought. University of Chicago press."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Kenta Takeuchi Souichirou Kubota Keisuke Suzuki Dai Hasegawa and Hiroshi Sakuta. 2017. Creating a Gesture-Speech Dataset for Speech-Based Automatic Gesture Generation. Springer International Publishing Cham 198--202. DOI:http:\/\/dx.doi.org\/10.1007\/978--3--319--58750--9_28 Kenta Takeuchi Souichirou Kubota Keisuke Suzuki Dai Hasegawa and Hiroshi Sakuta. 2017. Creating a Gesture-Speech Dataset for Speech-Based Automatic Gesture Generation. Springer International Publishing Cham 198--202. DOI:http:\/\/dx.doi.org\/10.1007\/978--3--319--58750--9_28","DOI":"10.1007\/978-3-319-58750-9_28"}],"event":{"name":"HAI '17: The Fifth International Conference on Human-Agent Interaction","location":"Bielefeld Germany","acronym":"HAI '17","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 5th International Conference on Human Agent Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3125739.3132594","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3125739.3132594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:11:11Z","timestamp":1750212671000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3125739.3132594"}},"subtitle":["A Challenge in Deep Learning Approach with Bi-Directional LSTM"],"short-title":[],"issued":{"date-parts":[[2017,10,27]]},"references-count":14,"alternative-id":["10.1145\/3125739.3132594","10.1145\/3125739"],"URL":"https:\/\/doi.org\/10.1145\/3125739.3132594","relation":{},"subject":[],"published":{"date-parts":[[2017,10,27]]},"assertion":[{"value":"2017-10-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}