{"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/e-branchformer-branchformer-with-enhanced","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","arxiv_id":"2210.00077","date":"2022-09-30","proceeding":null,"authors":["Kwangyoun Kim","Felix Wu","Yifan Peng","Jing Pan","Prashant Sridhar","Kyu J. Han","Shinji Watanabe"],"abstract":"Conformer, combining convolution and self-attention sequentially to capture both local and global information, has shown remarkable performance and is currently regarded as the state-of-the-art for automatic speech recognition (ASR). Several other studies have explored integrating convolution and self-attention but they have not managed to match Conformer's performance. The recently introduced Branchformer achieves comparable performance to Conformer by using dedicated branches of convolution and self-attention and merging local and global context from each branch. In this paper, we propose E-Branchformer, which enhances Branchformer by applying an effective merging method and stacking additional point-wise modules. E-Branchformer sets new state-of-the-art word error rates (WERs) 1.81% and 3.65% on LibriSpeech test-clean and test-other sets without using any external training data.","url_abs":"https://arxiv.org/abs/2210.00077v2","url_pdf":"https://arxiv.org/pdf/2210.00077v2.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":"e-branchformer-branchformer-with-enhanced","repo_url":"https://github.com/espnet/espnet","is_official":1,"mentioned_in_paper":1,"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":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"e-branchformer","method_name":"E-Branchformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"e-branchformer","name":"E-Branchformer","full_name":"E-Branchformer"}],"results":[{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"E-Branchformer (L) + Internal Language Model Estimation","rank_in_archive_order":15,"of":64,"metrics":{"Word Error Rate (WER)":"1.81"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-librispeech-test-other","task":"Speech Recognition","dataset":"LibriSpeech test-other","model":"E-Branchformer (L) + Internal Language Model Estimation","rank_in_archive_order":11,"of":53,"metrics":{"Word Error Rate (WER)":"3.65"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2210.00077","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}