{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:07:49Z","timestamp":1750223269537,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100022598","name":"Toray Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100022598","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JSPS KAKENHI","award":["JP22K12069"],"award-info":[{"award-number":["JP22K12069"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/jstsp.2022.3189279","type":"journal-article","created":{"date-parts":[[2022,7,7]],"date-time":"2022-07-07T19:28:58Z","timestamp":1657222138000},"page":"1480-1492","source":"Crossref","is-referenced-by-count":2,"title":["Automatic Spoken Language Acquisition Based on Observation and Dialogue"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6139-0642","authenticated-orcid":false,"given":"Ryota","family":"Komatsu","sequence":"first","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengzhou","family":"Gao","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxin","family":"Hou","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Tanaka","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Toyoda","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Kimura","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kent","family":"Hino","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4388-9017","authenticated-orcid":false,"given":"Yu","family":"Iwamoto","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kosuke","family":"Mori","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9913-4647","authenticated-orcid":false,"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Koganei, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8114-8450","authenticated-orcid":false,"given":"Takahiro","family":"Shinozaki","sequence":"additional","affiliation":[{"name":"Tokyo Institute of Technology, Meguro, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/11256-000"},{"issue":"1","key":"ref2","first-page":"26","article-title":"A review of B. F. Skinners verbal behavior","volume-title":"Language","volume":"35","author":"Chomsky","year":"1959"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2017.01918"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1533"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2017.11.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/S0305000900013167"},{"volume-title":"Artificial Intelligence: A Modern Approach","year":"1995","author":"Russell","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.00985"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.beproc.2010.11.007"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2020.0243"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053326"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2027"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA202152914.2021.9660413"},{"key":"ref14","article-title":"Pronunciation adaptive self speaking agent using wavegrad","volume-title":"Proc. 2nd Workshop Self-Supervised Learn. Audio Speech Process.","author":"Tanaka","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/89.260365"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(91)90020-Q"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2000-567"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog2601_4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00354-019-00084-w"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.02.026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-440"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.08.008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280477"},{"article-title":"On-line Q-learning using connectionist systems","year":"1994","author":"Rummery","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269008"},{"key":"ref28","first-page":"7365","article-title":"Unsupervised cross-modal alignment of speech and text embedding spaces","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chung","year":"2018"},{"key":"ref29","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Harwath","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref31","first-page":"1","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref32","first-page":"1","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref34","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415087"},{"key":"ref36","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Goodfellow","year":"2014"},{"key":"ref37","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref38","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688194"},{"key":"ref41","first-page":"1","article-title":"High fidelity speech synthesis with adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bikowski","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref43","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Song","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1897"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"issue":"39","key":"ref46","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Math. Learn. Res."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.7b00492"},{"key":"ref48","first-page":"2440","article-title":"End-to-end memory networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sukhbaatar","year":"2015"},{"article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"Warden","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"article-title":"OpenAI Gym","year":"2016","author":"Brockman","key":"ref52"},{"issue":"268","key":"ref53","first-page":"1","article-title":"Stable-Baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09817627.pdf?arnumber=9817627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T02:24:26Z","timestamp":1706063066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9817627\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":53,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3189279","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}