{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:10:09Z","timestamp":1772554209817,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341196","type":"proceedings-article","created":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T14:49:56Z","timestamp":1615819796000},"page":"5580-5587","source":"Crossref","is-referenced-by-count":6,"title":["Robot Sound Interpretation: Combining Sight and Sound in Learning-Based Control"],"prefix":"10.1109","author":[{"given":"Peixin","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuijing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haonan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katherine","family":"Driggs-Campbell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Python speech features","author":"lyons","year":"2013"},{"key":"ref38","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"engel","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref33","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref32","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref30","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref36","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018"},{"key":"ref35","article-title":"Openai baselines","author":"dhariwal","year":"2017"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2016.7502665"},{"key":"ref40","article-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning","author":"coumans","year":"2016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-011-9263-y"},{"key":"ref12","first-page":"2747","article-title":"A discriminative approach to grounded spoken language understanding in interactive robotics","author":"bastianelli","year":"0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2016.7846794"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918777627"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363576"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/1729881419851402"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v28i1.8929","article-title":"Improving domain-independent cloud-based speech recognition with domain-dependent phonetic post-processing","author":"twiefel","year":"2014","journal-title":"Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.17562\/PB-54-2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhs366"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/1064546053278973"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref5","article-title":"Grounded language learning in a simulated 3d world","author":"hermann","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/j.1749-6632.1990.tb48889.x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.00506"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(00)01463-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759137"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2858-16.2016"},{"key":"ref20","article-title":"Interactive grounded language acquisition and generalization in a 2d world","author":"yu","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968303"},{"key":"ref21","first-page":"2819","article-title":"Gated-attention architectures for task-oriented language grounding","author":"chaplot","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2001.939507"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.05.023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5772\/5786"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"2176","DOI":"10.1109\/IJCNN.2001.938504","article-title":"Robot speech learning via entropy guided lvq and memory association","volume":"3","author":"liu","year":"2001","journal-title":"International Joint Conference on Neural Networks (IJCNN)"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,24]]},"end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341196.pdf?arnumber=9341196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T14:51:51Z","timestamp":1671634311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341196","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}