{"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/contextnet-improving-convolutional-neural","title":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","arxiv_id":"2005.03191","date":"2020-05-07","proceeding":null,"authors":["Wei Han","Zhengdong Zhang","Yu Zhang","Jiahui Yu","Chung-Cheng Chiu","James Qin","Anmol Gulati","Ruoming Pang","Yonghui Wu"],"abstract":"Convolutional neural networks (CNN) have shown promising results for end-to-end speech recognition, albeit still behind other state-of-the-art methods in performance. In this paper, we study how to bridge this gap and go beyond with a novel CNN-RNN-transducer architecture, which we call ContextNet. ContextNet features a fully convolutional encoder that incorporates global context information into convolution layers by adding squeeze-and-excitation modules. In addition, we propose a simple scaling method that scales the widths of ContextNet that achieves good trade-off between computation and accuracy. We demonstrate that on the widely used LibriSpeech benchmark, ContextNet achieves a word error rate (WER) of 2.1%/4.6% without external language model (LM), 1.9%/4.1% with LM and 2.9%/7.0% with only 10M parameters on the clean/noisy LibriSpeech test sets. This compares to the previous best published system of 2.0%/4.6% with LM and 3.9%/11.3% with 20M parameters. The superiority of the proposed ContextNet model is also verified on a much larger internal dataset.","url_abs":"https://arxiv.org/abs/2005.03191v3","url_pdf":"https://arxiv.org/pdf/2005.03191v3.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":"contextnet-improving-convolutional-neural","repo_url":"https://github.com/Cross-Caps/STFADE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"contextnet-improving-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":"contextnet-improving-convolutional-neural","repo_url":"https://github.com/hasangchun/ContextNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"contextnet-improving-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":"contextnet-improving-convolutional-neural","repo_url":"https://github.com/openspeech-team/openspeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"contextnet-improving-convolutional-neural","repo_url":"https://github.com/upskyy/ContextNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"ContextNet(L)","rank_in_archive_order":17,"of":64,"metrics":{"Word Error Rate (WER)":"1.9"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"ContextNet(M)","rank_in_archive_order":20,"of":64,"metrics":{"Word Error Rate (WER)":"2"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"ContextNet(S)","rank_in_archive_order":36,"of":64,"metrics":{"Word Error Rate (WER)":"2.3"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"ContextNet(L)","rank_in_archive_order":18,"of":53,"metrics":{"Word Error Rate (WER)":"4.1"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"ContextNet(M)","rank_in_archive_order":27,"of":53,"metrics":{"Word Error Rate (WER)":"4.5"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"ContextNet(S)","rank_in_archive_order":33,"of":53,"metrics":{"Word Error Rate (WER)":"5.5"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.03191","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}