{"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-microsoft-2016-conversational-speech","title":"The Microsoft 2016 Conversational Speech Recognition System","arxiv_id":"1609.03528","date":"2016-09-12","proceeding":null,"authors":["W. Xiong","J. Droppo","X. Huang","F. Seide","M. Seltzer","A. Stolcke","D. Yu","G. Zweig"],"abstract":"We describe Microsoft's conversational speech recognition system, in which we\ncombine recent developments in neural-network-based acoustic and language\nmodeling to advance the state of the art on the Switchboard recognition task.\nInspired by machine learning ensemble techniques, the system uses a range of\nconvolutional and recurrent neural networks. I-vector modeling and lattice-free\nMMI training provide significant gains for all acoustic model architectures.\nLanguage model rescoring with multiple forward and backward running RNNLMs, and\nword posterior-based system combination provide a 20% boost. The best single\nsystem uses a ResNet architecture acoustic model with RNNLM rescoring, and\nachieves a word error rate of 6.9% on the NIST 2000 Switchboard task. The\ncombined system has an error rate of 6.2%, representing an improvement over\npreviously reported results on this benchmark task.","url_abs":"http://arxiv.org/abs/1609.03528v2","url_pdf":"http://arxiv.org/pdf/1609.03528v2.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":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-switchboard-hub500","task":"Speech Recognition","dataset":"Switchboard + Hub500","model":"Microsoft 2016","rank_in_archive_order":5,"of":30,"metrics":{"Percentage error":"6.2"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-switchboard-hub500","task":"Speech Recognition","dataset":"Switchboard + Hub500","model":"VGG/Resnet/LACE/BiLSTM acoustic model trained on SWB+Fisher+CH, N-gram + RNNLM language model trained on Switchboard+Fisher+Gigaword+Broadcast","rank_in_archive_order":6,"of":30,"metrics":{"Percentage error":"6.3"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-switchboard-hub500","task":"Speech Recognition","dataset":"Switchboard + Hub500","model":"RNNLM","rank_in_archive_order":10,"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":"VGG/Resnet/LACE/BiLSTM acoustic model trained on SWB+Fisher+CH, N-gram + RNNLM language model trained on Switchboard+Fisher+Gigaword+Broadcast","rank_in_archive_order":4,"of":12,"metrics":{"Percentage error":"11.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.03528","atlas_url":"https://app.syntology.ai/?focus=1609.03528","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":"1609.03528"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1609.03528\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1609.03528"},"call":"get_concepts_for_paper(arxiv_id=\"1609.03528\")"}],"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":"b24c929536fd912771ea148db82a3b84f6eaab5dc8b825541ec2b9037c425516","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}