{"url":"/dataset/gneutralspeech-male","name":"GneutralSpeech Male","full_name":null,"description_markdown":"A database containing high sam\u0002pling rate recordings of a single speaker reading sentences in Brazilian\r\nPortuguese with neutral voice, along with the corresponding text corpus.\r\nIntended for speech synthesis and automatic speech recognition applica\u0002tions, the dataset contains text extracted from a popular Brazilian news\r\nTV program, totalling roughly 20 h of audio spoken by a trained in\u0002dividual in a controlled environment. The text was normalized in the\r\nrecording process and special textual occurrences (e.g. acronyms, num\u0002bers, foreign names etc.) were replaced by their phonetic translation to\r\na readable text in Portuguese. There are no noticeable accidental sounds\r\nand background noise has been kept to a minimum in all audio samples.\r\n\r\nIntended for:\r\nTTS\r\nASR\r\nSpeech Enhancement\r\nVoice Conversion","description_withheld":null,"homepage":"https://www02.smt.ufrj.br/~gpa/propor2022/","introduced_date":"2021-05-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-corpus-of-neutral-voice-speech-in-brazilian","title":"A Corpus of Neutral Voice Speech in Brazilian Portuguese","first_author":"Pedro H. L. Leite","url":null},"license":{"name":"Custom","url":"https://www.kaggle.com/datasets/mediatechlab/gneutralspeech"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Speech Enhancement","url":"/task/speech-enhancement","datasets_with_task":"/datasets/task/speech-enhancement"},{"name":"Speech Synthesis","url":"/task/speech-synthesis","datasets_with_task":"/datasets/task/speech-synthesis"},{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"},{"name":"Text-To-Speech Synthesis","url":"/task/text-to-speech-synthesis","datasets_with_task":"/datasets/task/text-to-speech-synthesis"},{"name":"Voice Conversion","url":"/task/voice-conversion","datasets_with_task":"/datasets/task/voice-conversion"},{"name":"Voice Cloning","url":"/task/voice-cloning","datasets_with_task":"/datasets/task/voice-cloning"}],"languages":[{"name":"Portuguese","url":"/datasets/language/portuguese"}],"variants":["GneutralSpeech Male"],"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."}