{"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/a-fully-differentiable-beam-search-decoder","title":"A Fully Differentiable Beam Search Decoder","arxiv_id":"1902.06022","date":"2019-02-16","proceeding":null,"authors":["Ronan Collobert","Awni Hannun","Gabriel Synnaeve"],"abstract":"We introduce a new beam search decoder that is fully differentiable, making\nit possible to optimize at training time through the inference procedure. Our\ndecoder allows us to combine models which operate at different granularities\n(e.g. acoustic and language models). It can be used when target sequences are\nnot aligned to input sequences by considering all possible alignments between\nthe two. We demonstrate our approach scales by applying it to speech\nrecognition, jointly training acoustic and word-level language models. The\nsystem is end-to-end, with gradients flowing through the whole architecture\nfrom the word-level transcriptions. Recent research efforts have shown that\ndeep neural networks with attention-based mechanisms are powerful enough to\nsuccessfully train an acoustic model from the final transcription, while\nimplicitly learning a language model. Instead, we show that it is possible to\ndiscriminatively train an acoustic model jointly with an explicit and possibly\npre-trained language model.","url_abs":"http://arxiv.org/abs/1902.06022v1","url_pdf":"http://arxiv.org/pdf/1902.06022v1.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":"a-fully-differentiable-beam-search-decoder","repo_url":"https://github.com/johnhw/differentiable_sorting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.06022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.06022"}},"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/johnhw/differentiable_sorting","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"42959284096ea8a0","entry":"smoothmax","repo":"johnhw/differentiable_sorting","repo_kind":"listed","path":"differentiable_sorting/differentiable_sorting.py","file_url":"https://github.com/johnhw/differentiable_sorting/blob/HEAD/differentiable_sorting/differentiable_sorting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42959284096ea8a0"}},{"code_sha256_prefix":"66850af2b5403afd","entry":"softmax","repo":"johnhw/differentiable_sorting","repo_kind":"listed","path":"differentiable_sorting/differentiable_sorting.py","file_url":"https://github.com/johnhw/differentiable_sorting/blob/HEAD/differentiable_sorting/differentiable_sorting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"66850af2b5403afd"}},{"code_sha256_prefix":"e5a20e97a1d05749","entry":"softmax_smooth","repo":"johnhw/differentiable_sorting","repo_kind":"listed","path":"differentiable_sorting/differentiable_sorting.py","file_url":"https://github.com/johnhw/differentiable_sorting/blob/HEAD/differentiable_sorting/differentiable_sorting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e5a20e97a1d05749"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}