{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:38:59Z","timestamp":1730230739699,"version":"3.28.0"},"reference-count":17,"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\/icassp49357.2023.10096184","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Less Is More: A Unified Architecture for Device-Directed Speech Detection with Multiple Invocation Types"],"prefix":"10.1109","author":[{"given":"Oggi","family":"Rudovic","sequence":"first","affiliation":[{"name":"Apple"}]},{"given":"Wonil","family":"Chang","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Vineet","family":"Garg","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Pranay","family":"Dighe","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Pramod","family":"Simha","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Jack","family":"Berkowitz","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Ahmed H.","family":"Abdelaziz","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Sachin","family":"Kajarekar","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Erik","family":"Marchi","sequence":"additional","affiliation":[{"name":"Apple"}]},{"given":"Saurabh","family":"Adya","sequence":"additional","affiliation":[{"name":"Apple"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1428"},{"key":"ref12","article-title":"Attention is All You Need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414357"},{"key":"ref14","article-title":"Connectionist Temporal Classification with Maximum Entropy Regularization","volume":"31","author":"liu","year":"2018","journal-title":"Proc NeurIPS 2018"},{"journal-title":"Streaming intended query detection using e2e modeling for continued conversation","year":"2022","author":"chang","key":"ref11"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053781"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/app12041974"},{"key":"ref1","volume":"abs 2010 15446","author":"sigtia","year":"2020","journal-title":"Progressive Voice Trigger Detection Accuracy vs Latency"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11228"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1531"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462166"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268946"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054304"},{"journal-title":"Streaming on-device detection of device directed speech from voice and touch-based invocation","year":"2022","author":"rudovic","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462227"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-352"}],"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\/10096184.pdf?arnumber=10096184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:00:02Z","timestamp":1700506802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096184","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}