{"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/the-ibm-2016-english-conversational-telephone","title":"The IBM 2016 English Conversational Telephone Speech Recognition System","arxiv_id":"1604.08242","date":"2016-04-27","proceeding":null,"authors":["George Saon","Tom Sercu","Steven Rennie","Hong-Kwang J. Kuo"],"abstract":"We describe a collection of acoustic and language modeling techniques that\nlowered the word error rate of our English conversational telephone LVCSR\nsystem to a record 6.6% on the Switchboard subset of the Hub5 2000 evaluation\ntestset. On the acoustic side, we use a score fusion of three strong models:\nrecurrent nets with maxout activations, very deep convolutional nets with 3x3\nkernels, and bidirectional long short-term memory nets which operate on FMLLR\nand i-vector features. On the language modeling side, we use an updated model\n\"M\" and hierarchical neural network LMs.","url_abs":"http://arxiv.org/abs/1604.08242v2","url_pdf":"http://arxiv.org/pdf/1604.08242v2.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":"maxout","method_name":"Maxout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-switchboard-hub500","task":"Speech Recognition","dataset":"Switchboard + Hub500","model":"RNN + VGG + LSTM acoustic model trained on SWB+Fisher+CH, N-gram + \"model M\" + NNLM language model","rank_in_archive_order":7,"of":30,"metrics":{"Percentage error":"6.6"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-switchboard-hub500","task":"Speech Recognition","dataset":"Switchboard + Hub500","model":"IBM 2016","rank_in_archive_order":9,"of":30,"metrics":{"Percentage error":"6.9"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-swb_hub_500-wer","task":"Speech Recognition","dataset":"swb_hub_500 WER fullSWBCH","model":"RNN + VGG + LSTM acoustic model trained on SWB+Fisher+CH, N-gram + \"model M\" + NNLM language model","rank_in_archive_order":5,"of":12,"metrics":{"Percentage error":"12.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"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":"cd6d88e615dbd0f049607b9a14dbef27246fbd4a8b31dda7874f7c68e47b2c05","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}