{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/unified-streaming-and-non-streaming-two-pass","title":"Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition","arxiv_id":"2012.05481","date":"2020-12-10","proceeding":null,"authors":["BinBin Zhang","Di wu","Zhuoyuan Yao","Xiong Wang","Fan Yu","Chao Yang","Liyong Guo","Yaguang Hu","Lei Xie","Xin Lei"],"abstract":"In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. Our model adopts the hybrid CTC/attention architecture, in which the conformer layers in the encoder are modified. We propose a dynamic chunk-based attention strategy to allow arbitrary right context length. At inference time, the CTC decoder generates n-best hypotheses in a streaming way. The inference latency could be easily controlled by only changing the chunk size. The CTC hypotheses are then rescored by the attention decoder to get the final result. This efficient rescoring process causes very little sentence-level latency. Our experiments on the open 170-hour AISHELL-1 dataset show that, the proposed method can unify the streaming and non-streaming model simply and efficiently. On the AISHELL-1 test set, our unified model achieves 5.60% relative character error rate (CER) reduction in non-streaming ASR compared to a standard non-streaming transformer. The same model achieves 5.42% CER with 640ms latency in a streaming ASR system.","url_abs":"https://arxiv.org/abs/2012.05481v2","url_pdf":"https://arxiv.org/pdf/2012.05481v2.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":"unified-streaming-and-non-streaming-two-pass","repo_url":"https://github.com/TeaPoly/Conformer-Athena","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"unified-streaming-and-non-streaming-two-pass","repo_url":"https://github.com/Vill-Lab/2023-TMM-Grad-SAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unified-streaming-and-non-streaming-two-pass","repo_url":"https://github.com/joseewei/wenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unified-streaming-and-non-streaming-two-pass","repo_url":"https://github.com/xianchao-wu/wenet-deep-sparse-conformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unified-streaming-and-non-streaming-two-pass","repo_url":"https://github.com/PaddlePaddle/PaddleSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"sentence","task_name":"Sentence"},{"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-aishell-1","task":"Speech Recognition","dataset":"AISHELL-1","model":"U2","rank_in_archive_order":12,"of":18,"metrics":{"Params(M)":"47","Word Error Rate (WER)":"4.72"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.05481","atlas_url":"https://app.syntology.ai/?focus=2012.05481","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2012.05481"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.05481\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.05481"},"call":"get_concepts_for_paper(arxiv_id=\"2012.05481\")"}],"by_repo":[{"repo":"TeaPoly/Conformer-Athena","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2005.08100"],"harvested_for_calls":[{"arxiv_id":"2005.08100","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2005.08100"},"call":"get_harvested_code_for_paper(arxiv_id=\"2005.08100\")"}]},{"repo":"Vill-Lab/2023-TMM-Grad-SAS","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"joseewei/wenet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xianchao-wu/wenet-deep-sparse-conformer","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PaddlePaddle/PaddleSpeech","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2203.09690"],"harvested_for_calls":[{"arxiv_id":"2203.09690","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.09690"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.09690\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4f19db36e02334806d5ad97e7428e81baa5c46a9a261ab7e7d6ac9021cd95f88","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}