{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:39:29Z","timestamp":1730230769747,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096250","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Continuous Action Space-Based Spoken Language Acquisition Agent Using Residual Sentence Embedding and Transformer Decoder"],"prefix":"10.1109","author":[{"given":"Ryota","family":"Komatsu","sequence":"first","affiliation":[{"name":"Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Kimura","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"Shinozaki","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2000-567"},{"key":"ref35","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proc NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/89.260365"},{"key":"ref34","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"Proc ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053326"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-440"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852155"},{"key":"ref30","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref11","article-title":"Interactive fiction games: A colossal adventure","author":"hausknecht","year":"2019","journal-title":"Proc AAAI"},{"key":"ref33","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref10","first-page":"1","article-title":"Textworld: A learning environment for text-based games","author":"cote","year":"2018","journal-title":"Computer Games Workshop at ICML\/IJCAI 2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1533"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2017.11.008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3189279"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2027"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref18","article-title":"Pronunciation adaptive self speaking agent using wavegrad","author":"tanaka","year":"2022","journal-title":"Proc AAAI SAS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc ICLR"},{"key":"ref20","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc ICLR"},{"key":"ref22","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","volume":"29","author":"harwath","year":"2016","journal-title":"Proc NIPS"},{"key":"ref21","first-page":"719","article-title":"An embedded segmental K-means model for unsupervised segmentation and clustering of speech","author":"kamper","year":"2017","journal-title":"Proc ASRU"},{"key":"ref28","article-title":"Learning hierarchical discrete linguistic units from visually-grounded speech","author":"harwath","year":"2020","journal-title":"Proc ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/S0272263104363059"},{"key":"ref9","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1037\/11256-000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/S0305000900013167"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2017.01918"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.2307\/411334"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096250.pdf?arnumber=10096250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T19:03:39Z","timestamp":1698087819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096250","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}