{"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/delay-penalized-ctc-implemented-based-on","title":"Delay-penalized CTC implemented based on Finite State Transducer","arxiv_id":"2305.11539","date":"2023-05-19","proceeding":null,"authors":["Zengwei Yao","Wei Kang","Fangjun Kuang","Liyong Guo","Xiaoyu Yang","Yifan Yang","Long Lin","Daniel Povey"],"abstract":"Connectionist Temporal Classification (CTC) suffers from the latency problem when applied to streaming models. We argue that in CTC lattice, the alignments that can access more future context are preferred during training, thereby leading to higher symbol delay. In this work we propose the delay-penalized CTC which is augmented with latency penalty regularization. We devise a flexible and efficient implementation based on the differentiable Finite State Transducer (FST). Specifically, by attaching a binary attribute to CTC topology, we can locate the frames that firstly emit non-blank tokens on the resulting CTC lattice, and add the frame offsets to the log-probabilities. Experimental results demonstrate the effectiveness of our proposed delay-penalized CTC, which is able to balance the delay-accuracy trade-off. Furthermore, combining the delay-penalized transducer enables the CTC model to achieve better performance and lower latency. Our work is open-sourced and publicly available https://github.com/k2-fsa/k2.","url_abs":"https://arxiv.org/abs/2305.11539v1","url_pdf":"https://arxiv.org/pdf/2305.11539v1.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":"delay-penalized-ctc-implemented-based-on","repo_url":"https://github.com/k2-fsa/k2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.11539","atlas_url":"https://app.syntology.ai/?focus=2305.11539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11539"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/k2-fsa/k2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"c220cdebd07ec5f3","entry":"fix_for_boundary","repo":"k2-fsa/k2","repo_kind":"official","path":"k2/python/k2/rnnt_loss.py","file_url":"https://github.com/k2-fsa/k2/blob/HEAD/k2/python/k2/rnnt_loss.py","link_basis":"first_harvest_node","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":"c220cdebd07ec5f3"}},{"code_sha256_prefix":"e73c35c6c9d0edd1","entry":"get_aux_label_info","repo":"k2-fsa/k2","repo_kind":"official","path":"k2/python/k2/fsa.py","file_url":"https://github.com/k2-fsa/k2/blob/HEAD/k2/python/k2/fsa.py","link_basis":"first_harvest_node","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":"e73c35c6c9d0edd1"}},{"code_sha256_prefix":"2551b4f1c0679dda","entry":"get_rnnt_logprobs","repo":"k2-fsa/k2","repo_kind":"official","path":"k2/python/k2/rnnt_loss.py","file_url":"https://github.com/k2-fsa/k2/blob/HEAD/k2/python/k2/rnnt_loss.py","link_basis":"first_harvest_node","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":"2551b4f1c0679dda"}},{"code_sha256_prefix":"fbd6cb5be5ae9a02","entry":"rnnt_loss_simple","repo":"k2-fsa/k2","repo_kind":"official","path":"k2/python/k2/rnnt_loss.py","file_url":"https://github.com/k2-fsa/k2/blob/HEAD/k2/python/k2/rnnt_loss.py","link_basis":"first_harvest_node","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":"fbd6cb5be5ae9a02"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}