{"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/building-dnn-acoustic-models-for-large","title":"Building DNN Acoustic Models for Large Vocabulary Speech Recognition","arxiv_id":"1406.7806","date":"2014-06-30","proceeding":null,"authors":["Andrew L. Maas","Peng Qi","Ziang Xie","Awni Y. Hannun","Christopher T. Lengerich","Daniel Jurafsky","Andrew Y. Ng"],"abstract":"Deep neural networks (DNNs) are now a central component of nearly all\nstate-of-the-art speech recognition systems. Building neural network acoustic\nmodels requires several design decisions including network architecture, size,\nand training loss function. This paper offers an empirical investigation on\nwhich aspects of DNN acoustic model design are most important for speech\nrecognition system performance. We report DNN classifier performance and final\nspeech recognizer word error rates, and compare DNNs using several metrics to\nquantify factors influencing differences in task performance. Our first set of\nexperiments use the standard Switchboard benchmark corpus, which contains\napproximately 300 hours of conversational telephone speech. We compare standard\nDNNs to convolutional networks, and present the first experiments using\nlocally-connected, untied neural networks for acoustic modeling. We\nadditionally build systems on a corpus of 2,100 hours of training data by\ncombining the Switchboard and Fisher corpora. This larger corpus allows us to\nmore thoroughly examine performance of large DNN models -- with up to ten times\nmore parameters than those typically used in speech recognition systems. Our\nresults suggest that a relatively simple DNN architecture and optimization\ntechnique produces strong results. These findings, along with previous work,\nhelp establish a set of best practices for building DNN hybrid speech\nrecognition systems with maximum likelihood training. Our experiments in DNN\noptimization additionally serve as a case study for training DNNs with\ndiscriminative loss functions for speech tasks, as well as DNN classifiers more\ngenerally.","url_abs":"http://arxiv.org/abs/1406.7806v2","url_pdf":"http://arxiv.org/pdf/1406.7806v2.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":"building-dnn-acoustic-models-for-large","repo_url":"https://github.com/pannous/caffe-speech-recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok"}}],"tasks":[{"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-switchboard-hub500","task":"Speech Recognition","dataset":"Switchboard + Hub500","model":"DNN + Dropout","rank_in_archive_order":26,"of":30,"metrics":{"Percentage error":"15"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-switchboard-hub500","task":"Speech Recognition","dataset":"Switchboard + Hub500","model":"DNN","rank_in_archive_order":27,"of":30,"metrics":{"Percentage error":"16"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-swb_hub_500-wer","task":"Speech Recognition","dataset":"swb_hub_500 WER fullSWBCH","model":"DNN + Dropout","rank_in_archive_order":11,"of":12,"metrics":{"Percentage error":"19.1"},"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":[{"repo":"pannous/caffe-speech-recognition","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"38a75c16896a7ee5911b42da62e519fcdf703a24674b4b25a1d22879fd171af8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}