{"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/achieving-human-parity-in-conversational","title":"Achieving Human Parity in Conversational Speech Recognition","arxiv_id":"1610.05256","date":"2016-10-17","proceeding":null,"authors":["W. Xiong","J. Droppo","X. Huang","F. Seide","M. Seltzer","A. Stolcke","D. Yu","G. Zweig"],"abstract":"Conversational speech recognition has served as a flagship speech recognition\ntask since the release of the Switchboard corpus in the 1990s. In this paper,\nwe measure the human error rate on the widely used NIST 2000 test set, and find\nthat our latest automated system has reached human parity. The error rate of\nprofessional transcribers is 5.9% for the Switchboard portion of the data, in\nwhich newly acquainted pairs of people discuss an assigned topic, and 11.3% for\nthe CallHome portion where friends and family members have open-ended\nconversations. In both cases, our automated system establishes a new state of\nthe art, and edges past the human benchmark, achieving error rates of 5.8% and\n11.0%, respectively. The key to our system's performance is the use of various\nconvolutional and LSTM acoustic model architectures, combined with a novel\nspatial smoothing method and lattice-free MMI acoustic training, multiple\nrecurrent neural network language modeling approaches, and a systematic use of\nsystem combination.","url_abs":"http://arxiv.org/abs/1610.05256v2","url_pdf":"http://arxiv.org/pdf/1610.05256v2.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":[],"tasks":[{"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":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-switchboard-hub500","task":"Speech Recognition","dataset":"Switchboard + Hub500","model":"Microsoft 2016b","rank_in_archive_order":4,"of":30,"metrics":{"Percentage error":"5.8"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-switchboard-hub500","task":"Speech Recognition","dataset":"Switchboard + Hub500","model":"CNN-LSTM","rank_in_archive_order":8,"of":30,"metrics":{"Percentage error":"6.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1610.05256","atlas_url":"https://app.syntology.ai/?focus=1610.05256","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":"1610.05256"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1610.05256\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1610.05256"},"call":"get_concepts_for_paper(arxiv_id=\"1610.05256\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ff1648c8c916cbf5774c78aa9783f90272aabfad3bdebb416143e5e12ea7f255","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}