{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:35:40Z","timestamp":1730230540856,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747107","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"491-495","source":"Crossref","is-referenced-by-count":3,"title":["Streaming on-Device Detection of Device Directed Speech from Voice and Touch-Based Invocation"],"prefix":"10.1109","author":[{"given":"Ognjen Oggi","family":"Rudovic","sequence":"first","affiliation":[{"name":"Apple Inc"}]},{"given":"Akanksha","family":"Bindal","sequence":"additional","affiliation":[{"name":"Apple Inc"}]},{"given":"Vineet","family":"Garg","sequence":"additional","affiliation":[{"name":"Apple Inc"}]},{"given":"Pramod","family":"Simha","sequence":"additional","affiliation":[{"name":"Apple Inc"}]},{"given":"Pranay","family":"Dighe","sequence":"additional","affiliation":[{"name":"Apple Inc"}]},{"given":"Sachin","family":"Kajarekar","sequence":"additional","affiliation":[{"name":"Apple Inc"}]}],"member":"263","reference":[{"key":"ref10","article-title":"On-Device Streaming Transformer-Based End-to-End Speech Recognition","author":"oh","year":"0","journal-title":"Proc INTERSPEECH 2021"},{"key":"ref11","article-title":"Transformerbased acoustic modeling for streaming speech synthesis","author":"wu","year":"0","journal-title":"Proc INTERSPEECH 2021"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.21437\/Interspeech.2020-2464"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.21437\/Interspeech.2019-1363"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP39728.2021.9414777"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2021-1428"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP39728.2021.9414771"},{"year":"2020","author":"tong","article-title":"Streaming ResLSTM with Causal Mean Aggregation for Device-Directed Utterance Detection","key":"ref17"},{"key":"ref18","article-title":"Attention is All You Need","author":"vaswani","year":"0","journal-title":"Proc NeurIPS 2017"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.18653\/v1\/P19-1285"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICASSP.2018.8462227"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.21437\/Interspeech.2015-352"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICASSP.2018.8462166"},{"year":"2020","author":"sigtia","article-title":"Progressive Voice Trigger Detection: Accuracy vs Latency","key":"ref5"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.21437\/Interspeech.2021-1454"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP40776.2020.9053577"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.21437\/Interspeech.2018-1531"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ASRU46091.2019.9003749"},{"year":"2018","author":"bai","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","key":"ref1"},{"key":"ref20","article-title":"Connectionist Temporal Classification with Maximum Entropy Regularization","volume":"31","author":"liu","year":"2018","journal-title":"Proc NeurIPS 2018"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1007\/978-3-319-49409-8_7"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.21437\/Interspeech.2020-1330"},{"year":"2014","author":"kingma","article-title":"Adam: A method for stochastic optimization","key":"ref24"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1016\/j.ymssp.2020.107398"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1162\/neco.1997.9.8.1735"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747107.pdf?arnumber=9747107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:45Z","timestamp":1660594305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747107","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}