{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/the-ibm-2015-english-conversational-telephone","title":"The IBM 2015 English Conversational Telephone Speech Recognition System","arxiv_id":"1505.05899","date":"2015-05-21","proceeding":null,"authors":["George Saon","Hong-Kwang J. Kuo","Steven Rennie","Michael Picheny"],"abstract":"We describe the latest improvements to the IBM English conversational\ntelephone speech recognition system. Some of the techniques that were found\nbeneficial are: maxout networks with annealed dropout rates; networks with a\nvery large number of outputs trained on 2000 hours of data; joint modeling of\npartially unfolded recurrent neural networks and convolutional nets by\ncombining the bottleneck and output layers and retraining the resulting model;\nand lastly, sophisticated language model rescoring with exponential and neural\nnetwork LMs. These techniques result in an 8.0% word error rate on the\nSwitchboard part of the Hub5-2000 evaluation test set which is 23% relative\nbetter than our previous best published result.","url_abs":"http://arxiv.org/abs/1505.05899v1","url_pdf":"http://arxiv.org/pdf/1505.05899v1.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":"dropout","method_name":"Dropout"},{"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":"IBM 2015","rank_in_archive_order":11,"of":30,"metrics":{"Percentage error":"8.0"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}