{"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/3m-multi-loss-multi-path-and-multi-level","title":"3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition","arxiv_id":"2204.03178","date":"2022-04-07","proceeding":null,"authors":["Zhao You","Shulin Feng","Dan Su","Dong Yu"],"abstract":"Recently, Conformer based CTC/AED model has become a mainstream architecture for ASR. In this paper, based on our prior work, we identify and integrate several approaches to achieve further improvements for ASR tasks, which we denote as multi-loss, multi-path and multi-level, summarized as \"3M\" model. Specifically, multi-loss refers to the joint CTC/AED loss and multi-path denotes the Mixture-of-Experts(MoE) architecture which can effectively increase the model capacity without remarkably increasing computation cost. Multi-level means that we introduce auxiliary loss at multiple level of a deep model to help training. We evaluate our proposed method on the public WenetSpeech dataset and experimental results show that the proposed method provides 12.2%-17.6% relative CER improvement over the baseline model trained by Wenet toolkit. On our large scale dataset of 150k hours corpus, the 3M model has also shown obvious superiority over the baseline Conformer model. Code is publicly available at https://github.com/tencent-ailab/3m-asr.","url_abs":"https://arxiv.org/abs/2204.03178v2","url_pdf":"https://arxiv.org/pdf/2204.03178v2.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":"3m-multi-loss-multi-path-and-multi-level","repo_url":"https://github.com/tencent-ailab/3m-asr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-wenetspeech","task":"Speech Recognition","dataset":"WenetSpeech","model":"Conformer-MoE (64e)","rank_in_archive_order":2,"of":8,"metrics":{"Character Error Rate (CER)":"7.19"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-wenetspeech","task":"Speech Recognition","dataset":"WenetSpeech","model":"Conformer-MoE (32e)","rank_in_archive_order":4,"of":8,"metrics":{"Character Error Rate (CER)":"7.49"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-wenetspeech","task":"Speech Recognition","dataset":"WenetSpeech","model":"Conformer-MoE (16e)","rank_in_archive_order":5,"of":8,"metrics":{"Character Error Rate (CER)":"7.67"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.03178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03178"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tencent-ailab/3m-asr","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"27e028c9c3f1bfa1","entry":"read_char_dict","repo":"tencent-ailab/3m-asr","repo_kind":"official","path":"bin/recognize.py","file_url":"https://github.com/tencent-ailab/3m-asr/blob/HEAD/bin/recognize.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"27e028c9c3f1bfa1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}