{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:05:05Z","timestamp":1775199905150,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434681","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Joint Multimodal Contrastive Learning for Robust Spoken Term Detection and Keyword Spotting"],"prefix":"10.1109","author":[{"given":"Ramesh","family":"Gundluru","sequence":"first","affiliation":[{"name":"Indian Institute of Technology,Electrical Engineering,Hyderabad,India"}]},{"given":"Shubham","family":"Gupta","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Artificial Intelligence,Hyderabad,India"}]},{"given":"K","family":"Sri Rama Murty","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Electrical Engineering,Hyderabad,India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2438543"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1722"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1592","article-title":"Query-by-example search with discriminative neural acoustic word embeddings","author":"Settle","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/2404089"},{"key":"ref6","article-title":"Drop-dtw: Aligning common signal between sequences while dropping outliers","author":"Dvornik","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413827"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5220\/0008053402740281"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1109\/SLT.2016.7846310","article-title":"Discriminative acoustic word embeddings: Recurrent neural network-based approaches","author":"Settle","year":"2016"},{"key":"ref10","article-title":"Multi-view recurrent neural acoustic word embeddings","author":"He","year":"2016","journal-title":"arXiv preprint arXiv:1611.04496"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2016-82","article-title":"Audio word2vec: Unsupervised learning of audio segment representations using sequence-to-sequence autoencoder","author":"Chung","year":"2016"},{"key":"ref12","article-title":"A correspondence variational autoencoder for unsupervised acoustic word embeddings","author":"Peng","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178970"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1179","article-title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639241"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/TASLP.2021.3060805","article-title":"Improved acoustic word embeddings for zero-resource languages using multilingual transfer","author":"Kamper","year":"2021"},{"key":"ref17","first-page":"919","article-title":"Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation","volume-title":"2021 IEEE Spoken Language Technology Workshop (SLT)","author":"Jacobs"},{"key":"ref18","article-title":"Clap: Learning audio concepts from natural language supervision","author":"Elizalde","year":"2022"},{"key":"ref19","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref20","article-title":"Enhancing word discrimination and matching in query-by-example spoken term detection with acoustic word embeddings","volume-title":"International Conference on Natural Language and Speech Processing","author":"Chantangphol"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","volume-title":"Distance Metric Learning for Large Margin Nearest Neighbor Classification","volume":"10","author":"Weinberger","year":"2006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02172-5_2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683639"},{"key":"ref25","article-title":"Multilingual distributed representations without word alignment","author":"Hermann","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434681.pdf?arnumber=11434681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:14Z","timestamp":1775192294000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434681","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}