{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T18:04:31Z","timestamp":1745690671351,"version":"3.37.3"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NSF Space, High-Performance, and REsilient Computing Center\u2019s industry and agency members and by the IUCRC Program of the National Science Foundation","award":["CNS-1738783"],"award-info":[{"award-number":["CNS-1738783"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3426471","type":"journal-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T18:08:02Z","timestamp":1720721282000},"page":"123276-123293","source":"Crossref","is-referenced-by-count":2,"title":["Benchmarking Inference of Transformer-Based Transcription Models With Clustering on Embedded GPUs"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9270-8502","authenticated-orcid":false,"given":"Marika E.","family":"Schubert","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8777-4655","authenticated-orcid":false,"given":"David","family":"Langerman","sequence":"additional","affiliation":[{"name":"NSF Center of Space, High-Performance, and Resilient Computing, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9665-2879","authenticated-orcid":false,"given":"Alan D.","family":"George","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Baevski"},{"key":"ref2","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"Zhang","year":"2020","journal-title":"arXiv:2010.10504"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414641"},{"key":"ref4","first-page":"27826","article-title":"Unsupervised speech recognition","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Baevski"},{"key":"ref5","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Baevski"},{"key":"ref6","article-title":"Fast transformers with clustered attention","author":"Vyas","year":"2020","journal-title":"arXiv:2007.04825"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CONECCT52877.2021.9622586"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref9","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref12","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Language Resour. Eval. Conf.","author":"Ardila"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC55918.2022.00033"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref19","first-page":"1","article-title":"The kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understand.","author":"Povey"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000464"},{"volume-title":"Alexa Voice Service V20160207 bar Alexa Voice Service","year":"2016","key":"ref21"},{"volume-title":"Amazon Transcribe Features Amazon Web Services","year":"2022","key":"ref22"},{"key":"ref23","first-page":"1","article-title":"Vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Baevski"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"volume-title":"Speech-to-Text: Automatic Speech Recognition Google Cloud","year":"2022","key":"ref25"},{"key":"ref26","article-title":"Streaming end-to-end speech recognition for mobile devices","author":"He","year":"2018","journal-title":"arXiv:1811.06621"},{"key":"ref27","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv:1412.5567"},{"key":"ref28","first-page":"173","article-title":"Deep speech2: End-to-end speech recognition in English and Mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"48","author":"Amodei"},{"key":"ref29","article-title":"Mixed-precision training for NLP and speech recognition with OpenSeq2Seq","author":"Kuchaiev","year":"2018","journal-title":"arXiv:1805.10387"},{"key":"ref30","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"Lan","year":"2019","journal-title":"arXiv:1909.11942"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.66"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.250"},{"volume-title":"Apoorv2904\/fairseq: Facebook AI Research Sequence-to-Sequence Toolkit Written in Python","year":"2021","author":"Vyas","key":"ref33"},{"volume-title":"Power Management for Jetson TX2 Series Devices","year":"2022","key":"ref34"},{"key":"ref35","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume":"119","author":"Katharopoulos","year":"2020","journal-title":"Proc. Mach. Learn. Res."},{"volume-title":"PyTorch for Jetson","year":"2019","key":"ref36"},{"volume-title":"PyTorch Benchmark","year":"2020","author":"Schueroff","key":"ref37"},{"key":"ref38","article-title":"Full stack optimization of transformer inference: A survey","author":"Kim","year":"2023","journal-title":"arXiv:2302.14017"},{"volume-title":"Whitepaper: NVIDIA Telsa V100 GPU Architecture: The Worlds Most Advanced Data Center GPU","year":"2017","key":"ref39"},{"volume-title":"NVIDIA Jetson Xavier OEM Product Design Guide","year":"2018","key":"ref40"},{"volume-title":"NVIDIA Jetson TX2 NX System-on-Module Data Sheet","year":"2021","key":"ref41"},{"volume-title":"Rosie Embedded System With NVIDIA Jetson TX2\/TX2\u2014Connect Tech Inc","year":"2022","author":"Tech","key":"ref42"},{"volume-title":"GPGPU Cards | Curtiss-Wright Defense Solutions","year":"2022","key":"ref43"},{"volume-title":"AI Rugged Computer (Jetson TX2)","year":"2022","key":"ref44"},{"volume-title":"Proton Testing of NVidia Jetson TX2","year":"2019","author":"Wyrwas","key":"ref45"},{"volume-title":"Jetson Xavier NX Series System-on-Module Data Sheet","year":"2022","key":"ref46"},{"volume-title":"Hardware Architectural Specification ? NVDLA Documentation","year":"2021","key":"ref47"},{"volume-title":"NVIDIA Jetson AGX Xavier Series System-on-Module","year":"2022","key":"ref48"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/10380310\/10595070-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10595070.pdf?arnumber=10595070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T04:40:17Z","timestamp":1726029617000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10595070\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3426471","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}