{"url":"/dataset/nisp","name":"NISP","full_name":"NITK-IISc Multilingual Multi-accent Speaker Profiling","description_markdown":"This dataset contains speech recordings along with speaker physical parameters (height, weight, shoulder size, age ) as well as regional information and linguistic information.\r\n\r\nThere are a total of 345 speakers (219 male and 126 female). The dataset contains sentences that are taken out from newspapers. Each speaker has contributed about 4-5 minutes of data that includes recordings in both English and their mother tongue. The transcript for the text is provided in UTF-8 format.\r\n\r\nSource: [NISP](https://github.com/iiscleap/NISP-Dataset)","description_withheld":null,"homepage":"https://github.com/iiscleap/NISP-Dataset","introduced_date":"2020-07-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/nisp-a-multi-lingual-multi-accent-dataset-for","title":"NISP: A Multi-lingual Multi-accent Dataset for Speaker Profiling","first_author":"Shareef Babu Kalluri","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Telugu","url":"/datasets/language/telugu"},{"name":"Kannada","url":"/datasets/language/kannada"},{"name":"Malayalam","url":"/datasets/language/malayalam"}],"variants":["NISP"],"data_loaders":[{"repo":"https://github.com/iiscleap/NISP-Dataset","url":"https://github.com/iiscleap/NISP-Dataset","frameworks":[]}],"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."}