{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T22:40:03Z","timestamp":1729377603960,"version":"3.27.0"},"reference-count":36,"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\/icassp49357.2023.10095204","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":5,"title":["Context-Aware end-to-end ASR Using Self-Attentive Embedding and Tensor Fusion"],"prefix":"10.1109","author":[{"given":"Shuo-Yiin","family":"Chang","sequence":"first","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639044"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","year":"2019","author":"shen","key":"ref34"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054287"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1107"},{"key":"ref36","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-206"},{"year":"0","key":"ref30","article-title":"Artificial intelligence at google: Our principles"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2021-1643","article-title":"Advanced longcontext end-to-end speech recognition using context-expanded transformers","author":"hori","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-212"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054358"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-38"},{"key":"ref17","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"lee j devlin","year":"2019","journal-title":"Proc Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688079"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.733"},{"key":"ref18","article-title":"SentenceBERT: Sentence embeddings using siamese BERT networks","author":"reimers","year":"2019","journal-title":"Proc EMNLPIJCNLP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.04.020"},{"key":"ref25","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"Proc ICLR"},{"key":"ref20","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"Proc ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747418"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414716"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generated of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in google home","author":"kim","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1855"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref9","article-title":"Recognizing long-form speech using streaming end-to-end models","author":"chiu d rybach t sainath t strohman a narayanan","year":"2019","journal-title":"Proc ASRU"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref3","article-title":"Unified end-to-end speech recognition and endpointing for fast and efficient speech system","author":"li","year":"0","journal-title":"Proc SLT"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"}],"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\/10095204.pdf?arnumber=10095204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T22:09:27Z","timestamp":1729375767000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095204","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}