{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/jasper-an-end-to-end-convolutional-neural","title":"Jasper: An End-to-End Convolutional Neural Acoustic Model","arxiv_id":"1904.03288","date":"2019-04-05","proceeding":null,"authors":["Jason Li","Vitaly Lavrukhin","Boris Ginsburg","Ryan Leary","Oleksii Kuchaiev","Jonathan M. Cohen","Huyen Nguyen","Ravi Teja Gadde"],"abstract":"In this paper, we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data. Our model, Jasper, uses only 1D convolutions, batch normalization, ReLU, dropout, and residual connections. To improve training, we further introduce a new layer-wise optimizer called NovoGrad. Through experiments, we demonstrate that the proposed deep architecture performs as well or better than more complex choices. Our deepest Jasper variant uses 54 convolutional layers. With this architecture, we achieve 2.95% WER using a beam-search decoder with an external neural language model and 3.86% WER with a greedy decoder on LibriSpeech test-clean. We also report competitive results on the Wall Street Journal and the Hub5'00 conversational evaluation datasets.","url_abs":"https://arxiv.org/abs/1904.03288v3","url_pdf":"https://arxiv.org/pdf/1904.03288v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"jasper-an-end-to-end-convolutional-neural","repo_url":"https://github.com/TensorSpeech/TensorFlowASR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"jasper-an-end-to-end-convolutional-neural","repo_url":"https://github.com/marka17/digit-recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"jasper-an-end-to-end-convolutional-neural","repo_url":"https://github.com/msalhab96/SpeeQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"jasper-an-end-to-end-convolutional-neural","repo_url":"https://github.com/osmr/imgclsmob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"jasper-an-end-to-end-convolutional-neural","repo_url":"https://github.com/sooftware/OpenSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"jasper-an-end-to-end-convolutional-neural","repo_url":"https://github.com/sooftware/jasper-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"jasper-an-end-to-end-convolutional-neural","repo_url":"https://github.com/stefanpantic/asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"jasper-an-end-to-end-convolutional-neural","repo_url":"https://github.com/2023-MindSpore-1/ms-code-15/tree/main/jasper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"jasper-an-end-to-end-convolutional-neural","repo_url":"https://github.com/MindSpore-paper-code-2/code399/tree/main/jasper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"jasper-an-end-to-end-convolutional-neural","repo_url":"https://github.com/NVIDIA/OpenSeq2Seq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"}],"methods":[{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-hub500-switchboard","task":"Speech Recognition","dataset":"Hub5'00 SwitchBoard","model":"Jasper DR 10x5","rank_in_archive_order":3,"of":5,"metrics":{"CallHome":"16.2","SwitchBoard":"7.8"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Jasper DR 10x5 (+ Time/Freq Masks)","rank_in_archive_order":45,"of":64,"metrics":{"Word Error Rate (WER)":"2.84"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Jasper DR 10x5","rank_in_archive_order":46,"of":64,"metrics":{"Word Error Rate (WER)":"2.95"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"Jasper DR 10x5 (+ Time/Freq Masks)","rank_in_archive_order":43,"of":53,"metrics":{"Word Error Rate (WER)":"7.84"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"Jasper DR 10x5","rank_in_archive_order":45,"of":53,"metrics":{"Word Error Rate (WER)":"8.79"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-wsj-eval92","task":"Speech Recognition","dataset":"WSJ eval92","model":"Jasper 10x3","rank_in_archive_order":17,"of":17,"metrics":{"Word Error Rate (WER)":"6.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.03288","atlas_url":"https://app.syntology.ai/?focus=1904.03288","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}