{"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":"/dataset/aishell-1","name":"AISHELL-1","full_name":null,"description_markdown":"AISHELL-1 is a corpus for speech recognition research and building speech recognition systems for Mandarin. \r\n\r\nSource: [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](/paper/aishell-1-an-open-source-mandarin-speech)","description_withheld":null,"homepage":"http://www.openslr.org/33/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/aishell-1-an-open-source-mandarin-speech","title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","first_author":"Hui Bu","url":null},"license":{"name":"Apache-2","url":"http://www.openslr.org/33/"},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"Mandarin Chinese","url":"/datasets/language/mandarin-chinese"}],"variants":["AISHELL-1"],"data_loaders":[],"num_papers_in_archive":197,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-recognition-on-aishell-1","task":"Speech Recognition","dataset_variant":"AISHELL-1","rows":18,"metrics":["Word Error Rate (WER)","Params(M)"],"first_row_in_archive_order":{"model":"FireRedASR-AED","paper":"/paper/fireredasr-open-source-industrial-grade","metrics":{"Params(M)":"1,100","Word Error Rate (WER)":"0.55"},"code_links":[{"title":"fireredteam/fireredasr","url":"https://github.com/fireredteam/fireredasr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":16,"of":16,"counts":{"papers_with_a_benchmark_row":16,"with_a_code_link":13,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":16,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/fireredasr-open-source-industrial-grade","slug":"fireredasr-open-source-industrial-grade","title":"FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration","date":"2025-01-24","arxiv_id":"2501.14350","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cr-ctc-consistency-regularization-on-ctc-for","slug":"cr-ctc-consistency-regularization-on-ctc-for","title":"CR-CTC: Consistency regularization on CTC for improved speech recognition","date":"2024-10-07","arxiv_id":"2410.05101","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lightweight-transducer-based-on-frame-level","slug":"lightweight-transducer-based-on-frame-level","title":"Lightweight Transducer Based on Frame-Level Criterion","date":"2024-09-05","arxiv_id":"2409.13698","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/seed-asr-understanding-diverse-speech-and","slug":"seed-asr-understanding-diverse-speech-and","title":"Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition","date":"2024-07-05","arxiv_id":"2407.04675","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/qwen-audio-advancing-universal-audio","slug":"qwen-audio-advancing-universal-audio","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","date":"2023-11-14","arxiv_id":"2311.07919","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["qwenlm/qwen-audio"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qwen-audio-advancing-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2311.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07919"}}}},{"paper":"/paper/unimodal-aggregation-for-ctc-based-speech","slug":"unimodal-aggregation-for-ctc-based-speech","title":"Unimodal Aggregation for CTC-based Speech Recognition","date":"2023-09-15","arxiv_id":"2309.08150","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bat-boundary-aware-transducer-for-memory","slug":"bat-boundary-aware-transducer-for-memory","title":"BAT: Boundary aware transducer for memory-efficient and low-latency ASR","date":"2023-05-19","arxiv_id":"2305.11571","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/funasr-a-fundamental-end-to-end-speech","slug":"funasr-a-fundamental-end-to-end-speech","title":"FunASR: A Fundamental End-to-End Speech Recognition Toolkit","date":"2023-05-18","arxiv_id":"2305.11013","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/beyond-universal-transformer-block-reusing","slug":"beyond-universal-transformer-block-reusing","title":"Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition","date":"2023-03-23","arxiv_id":"2303.13072","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/knowledge-transfer-from-pre-trained-language","slug":"knowledge-transfer-from-pre-trained-language","title":"Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation","date":"2023-01-30","arxiv_id":"2301.13003","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/mmspeech-multi-modal-multi-task-encoder","slug":"mmspeech-multi-modal-multi-task-encoder","title":"MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition","date":"2022-11-29","arxiv_id":"2212.00500","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-mandarin-speech-recogntion-with","slug":"improving-mandarin-speech-recogntion-with","title":"Improving Mandarin Speech Recogntion with Block-augmented Transformer","date":"2022-07-24","arxiv_id":"2207.11697","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unified-streaming-and-non-streaming-two-pass","slug":"unified-streaming-and-non-streaming-two-pass","title":"Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition","date":"2020-12-10","arxiv_id":"2012.05481","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/cat-a-ctc-crf-based-asr-toolkit-bridging-the","slug":"cat-a-ctc-crf-based-asr-toolkit-bridging-the","title":"CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency","date":"2020-05-27","arxiv_id":"2005.13326","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-comparative-study-on-transformer-vs-rnn-in","slug":"a-comparative-study-on-transformer-vs-rnn-in","title":"A Comparative Study on Transformer vs RNN in Speech Applications","date":"2019-09-13","arxiv_id":"1909.06317","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/end-to-end-speech-recognition-with-adaptive","slug":"end-to-end-speech-recognition-with-adaptive","title":"End-to-end Speech Recognition with Adaptive Computation Steps","date":"2018-08-30","arxiv_id":"1808.10088","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/fireredasr-open-source-industrial-grade","slug":"fireredasr-open-source-industrial-grade","title":"FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration","date":"2025-01-24","arxiv_id":"2501.14350","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cr-ctc-consistency-regularization-on-ctc-for","slug":"cr-ctc-consistency-regularization-on-ctc-for","title":"CR-CTC: Consistency regularization on CTC for improved speech recognition","date":"2024-10-07","arxiv_id":"2410.05101","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lightweight-transducer-based-on-frame-level","slug":"lightweight-transducer-based-on-frame-level","title":"Lightweight Transducer Based on Frame-Level Criterion","date":"2024-09-05","arxiv_id":"2409.13698","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/seed-asr-understanding-diverse-speech-and","slug":"seed-asr-understanding-diverse-speech-and","title":"Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition","date":"2024-07-05","arxiv_id":"2407.04675","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/qwen-audio-advancing-universal-audio","slug":"qwen-audio-advancing-universal-audio","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","date":"2023-11-14","arxiv_id":"2311.07919","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":7,"official":{"repos":["qwenlm/qwen-audio"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qwen-audio-advancing-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2311.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07919"}}}},{"paper":"/paper/unimodal-aggregation-for-ctc-based-speech","slug":"unimodal-aggregation-for-ctc-based-speech","title":"Unimodal Aggregation for CTC-based Speech Recognition","date":"2023-09-15","arxiv_id":"2309.08150","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bat-boundary-aware-transducer-for-memory","slug":"bat-boundary-aware-transducer-for-memory","title":"BAT: Boundary aware transducer for memory-efficient and low-latency ASR","date":"2023-05-19","arxiv_id":"2305.11571","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/funasr-a-fundamental-end-to-end-speech","slug":"funasr-a-fundamental-end-to-end-speech","title":"FunASR: A Fundamental End-to-End Speech Recognition Toolkit","date":"2023-05-18","arxiv_id":"2305.11013","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/beyond-universal-transformer-block-reusing","slug":"beyond-universal-transformer-block-reusing","title":"Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition","date":"2023-03-23","arxiv_id":"2303.13072","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/knowledge-transfer-from-pre-trained-language","slug":"knowledge-transfer-from-pre-trained-language","title":"Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation","date":"2023-01-30","arxiv_id":"2301.13003","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/mmspeech-multi-modal-multi-task-encoder","slug":"mmspeech-multi-modal-multi-task-encoder","title":"MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition","date":"2022-11-29","arxiv_id":"2212.00500","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-mandarin-speech-recogntion-with","slug":"improving-mandarin-speech-recogntion-with","title":"Improving Mandarin Speech Recogntion with Block-augmented Transformer","date":"2022-07-24","arxiv_id":"2207.11697","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unified-streaming-and-non-streaming-two-pass","slug":"unified-streaming-and-non-streaming-two-pass","title":"Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition","date":"2020-12-10","arxiv_id":"2012.05481","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/cat-a-ctc-crf-based-asr-toolkit-bridging-the","slug":"cat-a-ctc-crf-based-asr-toolkit-bridging-the","title":"CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency","date":"2020-05-27","arxiv_id":"2005.13326","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-comparative-study-on-transformer-vs-rnn-in","slug":"a-comparative-study-on-transformer-vs-rnn-in","title":"A Comparative Study on Transformer vs RNN in Speech Applications","date":"2019-09-13","arxiv_id":"1909.06317","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/end-to-end-speech-recognition-with-adaptive","slug":"end-to-end-speech-recognition-with-adaptive","title":"End-to-end Speech Recognition with Adaptive Computation Steps","date":"2018-08-30","arxiv_id":"1808.10088","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/aishell-1/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/aishell-1/papers/ran/1","json":"/dataset/aishell-1/papers/ran/1.json","rows":1}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":1,"samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":7,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":3,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/speech-recognition-on-aishell-1","since_archive":"/sota/speech-recognition-on-aishell-1#since-judged","papers_judged":3,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"a0cc797732015ecb24d670f1a3b7f4e9e79d1738712006ef72132c249b4e1e13","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}