{"url":"/dataset/masri-headset","name":"MASRI-HEADSET","full_name":null,"description_markdown":"MASRI-HEADSET is a corpus that was developed by the MASRI project at the University of Malta. It consists of 8 hours of speech paired with text, recorded by using short text snippets in a laboratory environment. The speakers were recruited from different geographical locations all over the Maltese islands, and were roughly evenly distributed by gender. \r\n\r\nSource: [MASRI-HEADSET: A Maltese Corpus for Speech Recognition](/paper/masri-headset-a-maltese-corpus-for-speech-1)","description_withheld":null,"homepage":"https://www.um.edu.mt/projects/masri/index.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/masri-headset-a-maltese-corpus-for-speech-1","title":"MASRI-HEADSET: A Maltese Corpus for Speech Recognition","first_author":"Carlos Mena","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"}],"languages":[{"name":"Maltese","url":"/datasets/language/maltese"}],"variants":["MASRI-HEADSET"],"data_loaders":[],"num_papers_in_archive":2,"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":"2026-09-24T18:15:14+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."}