{"url":"/dataset/arvoice","name":"ArVoice","full_name":"ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis","description_markdown":"We introduce ArVoice, a multi-speaker Modern Standard Arabic (MSA) speech corpus with diacritized transcriptions, intended for multi-speaker speech synthesis, and can be useful for other tasks such as speech-based diacritic restoration, voice conversion, and deepfake detection. \r\n\r\nArVoice comprises:\r\n (1) a new professionally recorded set from six voice talents with diverse demographics, \r\n (2) a modified subset of the Arabic Speech Corpus; and \r\n (3) high-quality synthetic speech from two commercial systems. \r\n\r\nThe complete corpus consists of a total of 83.52 hours of speech across 11 voices; around 10 hours consist of human voices from 7 speakers. We train three open-source TTS and two voice conversion systems to illustrate the use cases of the dataset. The corpus is available for research use.","description_withheld":null,"homepage":"https://huggingface.co/datasets/MBZUAI/ArVoice","introduced_date":"2025-05-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/arvoice-a-multi-speaker-dataset-for-arabic","title":"ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis","first_author":"Hawau Olamide Toyin","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Voice Conversion","url":"/task/voice-conversion","datasets_with_task":"/datasets/task/voice-conversion"},{"name":"Text to Speech","url":"/task/text-to-speech","datasets_with_task":"/datasets/task/text-to-speech"},{"name":"fake voice detection","url":"/task/fake-voice-detection","datasets_with_task":"/datasets/task/fake-voice-detection"},{"name":"Zero-Shot Multi-Speaker TTS","url":"/task/zero-shot-multi-speaker-tts","datasets_with_task":"/datasets/task/zero-shot-multi-speaker-tts"}],"languages":[{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Standard Arabic","url":"/datasets/language/standard-arabic"}],"variants":["ArVoice"],"data_loaders":[],"num_papers_in_archive":1,"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."}