{"url":"/dataset/switchboard-1-corpus","name":"Switchboard-1 Corpus","full_name":null,"description_markdown":"The Switchboard-1 Telephone Speech Corpus (LDC97S62) consists of approximately 260 hours of speech and was originally collected by Texas Instruments in 1990-1, under DARPA sponsorship. The first release of the corpus was published by NIST and distributed by the LDC in 1992-3.\r\n\r\nSwitchboard is a collection of about 2,400 two-sided telephone conversations among 543 speakers (302 male, 241 female) from all areas of the United States. A computer-driven robot operator system handled the calls, giving the caller appropriate recorded prompts, selecting and dialing another person (the callee) to take part in a conversation, introducing a topic for discussion and recording the speech from the two subjects into separate channels until the conversation was finished. About 70 topics were provided, of which about 50 were used frequently. Selection of topics and callees was constrained so that: (1) no two speakers would converse together more than once and (2) no one spoke more than once on a given topic.\r\n\r\nSource: [https://catalog.ldc.upenn.edu/LDC97S62](https://catalog.ldc.upenn.edu/LDC97S62)","description_withheld":null,"homepage":"https://catalog.ldc.upenn.edu/LDC97S62","introduced_date":"2008-09-01","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Dialogue Act Classification","url":"/task/dialogue-act-classification","datasets_with_task":"/datasets/task/dialogue-act-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Switchboard corpus","Switchboard-1 Corpus"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/dialogue-act-classification-on-switchboard","task":"Dialogue Act Classification","dataset_variant":"Switchboard corpus","rows":11,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"HGRU + Beam Search + Guided attention","paper":"/paper/guiding-attention-in-sequence-to-sequence","metrics":{"Accuracy":"85.0"},"code_links":[{"title":"venkat-ravilla/DAP","url":"https://github.com/venkat-ravilla/DAP"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/speaker-turn-modeling-for-dialogue-act","title":"Speaker Turn Modeling for Dialogue Act Classification","date":"2021-09-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-pre-training-for-sequence","title":"Hierarchical Pre-training for Sequence Labelling in Spoken Dialog","date":"2020-09-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/guiding-attention-in-sequence-to-sequence","title":"Guiding attention in Sequence-to-sequence models for Dialogue Act prediction","date":"2020-02-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dialogue-act-classification-with-context","title":"Dialogue Act Classification with Context-Aware Self-Attention","date":"2019-04-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improved-dynamic-memory-network-for-dialogue","title":"Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training","date":"2018-11-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-dual-attention-hierarchical-recurrent","title":"A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification","date":"2018-10-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/conversational-analysis-using-utterance-level","title":"Conversational Analysis using Utterance-level Attention-based Bidirectional Recurrent Neural Networks","date":"2018-05-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-context-based-approach-for-dialogue-act","title":"A Context-based Approach for Dialogue Act Recognition using Simple Recurrent Neural Networks","date":"2018-05-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dialogue-act-recognition-via-crf-attentive","title":"Dialogue Act Recognition via CRF-Attentive Structured Network","date":"2017-11-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dialogue-act-sequence-labeling-using","title":"Dialogue Act Sequence Labeling using Hierarchical encoder with CRF","date":"2017-09-13","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/sequential-short-text-classification-with","title":"Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks","date":"2016-03-12","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}