{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:03:34Z","timestamp":1725807814084},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022592","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"100-107","source":"Crossref","is-referenced-by-count":1,"title":["Accelerator-Aware Training for Transducer-Based Speech Recognition"],"prefix":"10.1109","volume":"30","author":[{"given":"Suhaila M.","family":"Shakiah","sequence":"first","affiliation":[{"name":"Alexa Machine Learning, Amazon.com,USA"}]},{"given":"Rupak Vignesh","family":"Swaminathan","sequence":"additional","affiliation":[{"name":"Alexa Machine Learning, Amazon.com,USA"}]},{"given":"Hieu Duy","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Alexa Machine Learning, Amazon.com,USA"}]},{"given":"Raviteja","family":"Chinta","sequence":"additional","affiliation":[{"name":"Amazon.com,Hardware Compute Group,USA"}]},{"given":"Tariq","family":"Afzal","sequence":"additional","affiliation":[{"name":"Amazon.com,Hardware Compute Group,USA"}]},{"given":"Nathan","family":"Susanj","sequence":"additional","affiliation":[{"name":"Alexa Machine Learning, Amazon.com,USA"}]},{"given":"Athanasios","family":"Mouchtaris","sequence":"additional","affiliation":[{"name":"Alexa Machine Learning, Amazon.com,USA"}]},{"given":"Grant P.","family":"Strimel","sequence":"additional","affiliation":[{"name":"Alexa Machine Learning, Amazon.com,USA"}]},{"given":"Ariya","family":"Rastrow","sequence":"additional","affiliation":[{"name":"Alexa Machine Learning, Amazon.com,USA"}]}],"member":"263","reference":[{"journal-title":"Fastemit Low-latency streaming asr with sequence-level emission regularization","year":"2021","author":"yu","key":"ref13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413844"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-712"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414652"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-354"},{"key":"ref10","article-title":"Codert: Distilling encoder representations with co-learning for transducer-based speech recognition","author":"vignesh","year":"2021","journal-title":"Pro-ceedings of the Annual Conference of the Inter-national Speech Communication Association (Inter-speech)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"journal-title":"Exploring Transformers for Large-Scale Speech Recognition","year":"2020","author":"lu","key":"ref1"},{"journal-title":"On the efficient representation and execution of deep acoustic models","year":"2016","author":"alvarez","key":"ref17"},{"key":"ref16","article-title":"Quantization aware training with absolute-cosine reg-ularization for automatic speech recognition","author":"nguyen","year":"2020","journal-title":"Pro-ceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"journal-title":"Deep compression Compressing deep neural networks with pruning trained quantization and huffman coding","year":"2016","author":"han","key":"ref19"},{"journal-title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","year":"2017","author":"jacob","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2009.5118213"},{"key":"ref23","article-title":"On the quantization of recurrent neural networks","author":"li","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT.2008.131"},{"key":"ref25","first-page":"856","article-title":"A digital circuit design of hyperbolic tangent sigmoid function for neural networks","author":"lin","year":"2008","journal-title":"2008 IEEE International Symposium on Circuits and Systems"},{"key":"ref20","article-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","author":"zhu","year":"2018","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref22","first-page":"2093","article-title":"Accelerator-aware pruning for con-volutional neural networks","volume":"30","author":"kang","year":"2019","journal-title":"IEEE Trans Cir cuits and Systems for Video Technology"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413844"},{"journal-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","year":"2013","author":"bengio","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","article-title":"Simple recurrent units for highly parallelizable recurrence","author":"lei","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413905"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10844"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref6","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proceedings of the International Confer-ence on Machine Learning (ICML)"},{"key":"ref5","article-title":"Optimizing speech recognition for the edge","author":"shangguan","year":"2019","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022592.pdf?arnumber=10022592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T17:08:18Z","timestamp":1676912898000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022592\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022592","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}