{"url":"/dataset/mavs","name":"MAVS","full_name":"Multilingual Audio-Visual Smartphone dataset","description_markdown":"**MAVS** is an audio-visual smartphone dataset captured in five different recent smartphones. This new dataset contains 103 subjects captured in three different sessions considering the different real-world scenarios. Three different languages are acquired in this dataset to include the problem of language dependency of the speaker recognition systems.","description_withheld":null,"homepage":"https://docs.google.com/forms/d/e/1FAIpQLSfTMqnQj8KNoUi1Ms1tx8Ewgil2l4wAAJVaKUJs6VkWfjAo4w/viewform","introduced_date":"2021-09-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/multilingual-audio-visual-smartphone-dataset","title":"Multilingual Audio-Visual Smartphone Dataset And Evaluation","first_author":"Hareesh Mandalapu","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speaker Recognition","url":"/task/speaker-recognition","datasets_with_task":"/datasets/task/speaker-recognition"}],"languages":[],"variants":["MAVS"],"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."}