{"url":"/dataset/clovacall","name":"ClovaCall","full_name":null,"description_markdown":"**ClovaCall** is a new large-scale Korean call-based speech corpus under a goal-oriented dialog scenario from more than 11,000 people. The raw dataset of ClovaCall includes approximately 112,000 pairs of a short sentence and its corresponding spoken utterance in a restaurant reservation domain.\n\nSource: [https://github.com/ClovaAI/ClovaCall](https://github.com/ClovaAI/ClovaCall)","description_withheld":null,"homepage":"https://github.com/ClovaAI/ClovaCall","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/clovacall-korean-goal-oriented-dialog-speech","title":"ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers","first_author":"Jung-Woo Ha","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Open-Domain Dialog","url":"/task/open-domain-dialog","datasets_with_task":"/datasets/task/open-domain-dialog"},{"name":"Goal-Oriented Dialog","url":"/task/goal-oriented-dialog","datasets_with_task":"/datasets/task/goal-oriented-dialog"}],"languages":[{"name":"Korean","url":"/datasets/language/korean"}],"variants":["ClovaCall"],"data_loaders":[{"repo":"https://github.com/ClovaAI/ClovaCall","url":"https://github.com/ClovaAI/ClovaCall","frameworks":["pytorch"]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+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."}