{"url":"/dataset/voices","name":"VOICES","full_name":"Voices Obscured In Complex Environmental Settings","description_markdown":"The VOICES corpus is a dataset to promote speech and signal processing research of speech recorded by far-field microphones in noisy room conditions. \r\n\r\nFor this corpus, audio was recorded in furnished rooms with background noise played in conjunction with foreground speech selected from the LibriSpeech corpus. Multiple sessions were recorded in each room to accommodate for all foreground speech-background noise combinations. Audio was recorded using twelve microphones placed throughout the room, resulting in 120 hours of audio per microphone.","description_withheld":null,"homepage":"https://registry.opendata.aws/lab41-sri-voices/","introduced_date":"2018-05-15","introduced_date_note":null,"introduced_by":{"paper":null,"title":"Voices Obscured in Complex Environmental Settings (VOICES) corpus","first_author":null,"url":null},"license":{"name":"Creative Commons BY 4.0","url":null},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["VOICES"],"data_loaders":[],"num_papers_in_archive":48,"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."}