{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:18:34Z","timestamp":1774419514510,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890820","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Unsupervised Acoustic Word Embedding with Visual-Grounded Speech Model and Novel Word-level ABX Evaluation Schemes"],"prefix":"10.1109","author":[{"given":"Mau","family":"Nguyen","sequence":"first","affiliation":[{"name":"JAIST,School of Information Science,Nomi,Japan"}]},{"given":"Shinobu","family":"Hasegawa","sequence":"additional","affiliation":[{"name":"JAIST,Center of IDER,Nomi,Japan"}]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"NAIST,School of Information Science,Ikoma,Japan"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"9","article-title":"An iot based voice controlled blind stick to guide blind people","volume":"9","author":"Pathak","year":"2020","journal-title":"International Journal of Engineering Inventions"},{"key":"ref2","article-title":"Multi-view recurrent neural acoustic word embeddings","author":"He","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1353\/lan.1992.0075"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"ref6","first-page":"745","article-title":"Audio word2vec: Unsupervised learning of acoustic word embeddings","author":"Chung","year":"2016","journal-title":"Interspeech"},{"key":"ref7","first-page":"3406","article-title":"Efficient acoustic word embedding learning using unsupervised subword modeling","volume-title":"ICASSP 2018 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Yang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00080"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-441"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1057"},{"key":"ref11","first-page":"1","article-title":"Representations of language in a model of visually grounded speech signal","volume":"22","author":"Zhu","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","first-page":"1234","article-title":"Fast-slow transformer for visually grounding speech","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Li"},{"key":"ref13","article-title":"Temporal context in unsupervised learning of speech features","author":"Synnaeve","year":"2014","journal-title":"Interspeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2362"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683639"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2022-10652","article-title":"Word discovery in visually grounded, self-supervised speech models","author":"Peng","year":"2022"},{"key":"ref18","author":"Chrupa\u0142a","year":"2017","journal-title":"Synthetically spoken coco"},{"key":"ref19","first-page":"11","article-title":"Mel frequency cepstral coefficients for music modeling","volume-title":"ISMIR","volume":"270","author":"Logan","year":"2000"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/S0025100300004291"},{"key":"ref22","author":"Heeringa","year":"2004","journal-title":"Measuring dialect pronunciation differences using levenshtein distance"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163965"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707765"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2517567"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890820.pdf?arnumber=10890820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:16Z","timestamp":1774416196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890820\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890820","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}