{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T05:40:07Z","timestamp":1747201207797,"version":"3.40.5"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T00:00:00Z","timestamp":1741219200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T00:00:00Z","timestamp":1741219200000},"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":[[2025,3,6]]},"DOI":"10.1109\/ncc63735.2025.10983304","type":"proceedings-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:43:35Z","timestamp":1747158215000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Duration-Aware Phone Embedding Upsampling for Open Vocabulary Keyword Spotting"],"prefix":"10.1109","author":[{"given":"Ramesh","family":"Gundluru","sequence":"first","affiliation":[{"name":"Indian Institute of Technology,Speech Information Processing Lab,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naveen","family":"Doppa","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Speech Information Processing Lab,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sri Rama Murty","family":"K","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Speech Information Processing Lab,Hyderabad,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-352"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-753"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268974"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.08.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953164"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472820"},{"key":"ref9","article-title":"Small-footprint open-vocabulary keyword spotting with quantized lstm networks","author":"Bluche","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74695-9_23"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2759726"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1846"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2022-580","article-title":"Learning audio-text agreement for open-vocabulary keyword spotting","volume-title":"Interspeech","author":"Shin","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-478"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-597"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446912"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/NCC60321.2024.10485678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414577"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3301239"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref21","article-title":"Highway networks","author":"Srivastava","year":"2015","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1399"},{"key":"ref26","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society","author":"Povey","year":"2011"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","volume-title":"Interspeech","author":"Wang","year":"2017"}],"event":{"name":"2025 National Conference on Communications (NCC)","start":{"date-parts":[[2025,3,6]]},"location":"New Delhi, India","end":{"date-parts":[[2025,3,9]]}},"container-title":["2025 National Conference on Communications (NCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10982528\/10982694\/10983304.pdf?arnumber=10983304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T05:23:59Z","timestamp":1747200239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10983304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ncc63735.2025.10983304","relation":{},"subject":[],"published":{"date-parts":[[2025,3,6]]}}}