{"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/deep-sparse-conformer-for-speech-recognition","title":"Deep Sparse Conformer for Speech Recognition","arxiv_id":"2209.00260","date":"2022-09-01","proceeding":null,"authors":["Xianchao Wu"],"abstract":"Conformer has achieved impressive results in Automatic Speech Recognition (ASR) by leveraging transformer's capturing of content-based global interactions and convolutional neural network's exploiting of local features. In Conformer, two macaron-like feed-forward layers with half-step residual connections sandwich the multi-head self-attention and convolution modules followed by a post layer normalization. We improve Conformer's long-sequence representation ability in two directions, \\emph{sparser} and \\emph{deeper}. We adapt a sparse self-attention mechanism with $\\mathcal{O}(L\\text{log}L)$ in time complexity and memory usage. A deep normalization strategy is utilized when performing residual connections to ensure our training of hundred-level Conformer blocks. On the Japanese CSJ-500h dataset, this deep sparse Conformer achieves respectively CERs of 5.52\\%, 4.03\\% and 4.50\\% on the three evaluation sets and 4.16\\%, 2.84\\% and 3.20\\% when ensembling five deep sparse Conformer variants from 12 to 16, 17, 50, and finally 100 encoder layers.","url_abs":"https://arxiv.org/abs/2209.00260v1","url_pdf":"https://arxiv.org/pdf/2209.00260v1.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":"deep-sparse-conformer-for-speech-recognition","repo_url":"https://github.com/xianchao-wu/wenet-deep-sparse-conformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}