{"url":"/dataset/dirha","name":"DIRHA","full_name":"Distant-speech Interaction for Robust Home Applications","description_markdown":"**DIRHA**-English is a multi-microphone database composed of real and simulated sequences of 1-minute. The overall corpus is composed of different types of sequences including: 1) Phonetically-rich sentences; 2) WSJ 5-k utterances; 3) WSJ 20-k utterances; 4) Conversational speech (also including keywords and commands).\r\nThe sequences are available for both UK and US English at 48 kHz. The DIRHA-English dataset offers the possibility to work with a very large number of microphone channels, to use of microphone arrays having different characteristics and to work considering different speech recognition tasks (e.g., phone-loop, keyword spotting, ASR with small and very large language models).\r\n\r\nSource: [The DIRHA-English Corpus](http://dirha.fbk.eu/DIRHA_English)\r\nImage Source: [https://arxiv.org/pdf/1710.02560v1.pdf](https://arxiv.org/pdf/1710.02560v1.pdf)","description_withheld":null,"homepage":"http://dirha.fbk.eu/DIRHA_English","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-dirha-english-corpus-and-related-tasks","title":"The DIRHA-English corpus and related tasks for distant-speech recognition in domestic environments","first_author":"Mirco Ravanelli","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Distant Speech Recognition","url":"/task/distant-speech-recognition","datasets_with_task":"/datasets/task/distant-speech-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DIRHA English WSJ","DIRHA"],"data_loaders":[],"num_papers_in_archive":19,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/distant-speech-recognition-on-dirha-english","task":"Distant Speech Recognition","dataset_variant":"DIRHA English WSJ","rows":3,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"Li-GRU","paper":"/paper/the-pytorch-kaldi-speech-recognition-toolkit","metrics":{"Word Error Rate (WER)":"23.9"},"code_links":[{"title":"mravanelli/pytorch-kaldi","url":"https://github.com/mravanelli/pytorch-kaldi"},{"title":"wponghiran/imp-snns-for-sl","url":"https://github.com/wponghiran/imp-snns-for-sl"},{"title":"xpz123/pytorch-kaldi","url":"https://github.com/xpz123/pytorch-kaldi"},{"title":"NOEPG/pytorch-kaldi","url":"https://github.com/NOEPG/pytorch-kaldi"},{"title":"Baileyswu/pytorch-hmm-vae","url":"https://github.com/Baileyswu/pytorch-hmm-vae"},{"title":"ayyucedemirbas/gcommands_12_classes","url":"https://github.com/ayyucedemirbas/gcommands_12_classes"},{"title":"yrhvivian/pytorch-kaldi","url":"https://github.com/yrhvivian/pytorch-kaldi"},{"title":"PeiyanFlying/https-github.com-PeiyanFlying-pytorch-kaldi","url":"https://github.com/PeiyanFlying/https-github.com-PeiyanFlying-pytorch-kaldi"},{"title":"amikey/pytorch-kaldi","url":"https://github.com/amikey/pytorch-kaldi"},{"title":"Dahee96/Seq2seq-","url":"https://github.com/Dahee96/Seq2seq-"},{"title":"walterheymans/pytorch-kaldi-gan","url":"https://github.com/walterheymans/pytorch-kaldi-gan"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/learning-problem-agnostic-speech","title":"Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks","date":"2019-04-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/interpretable-convolutional-filters-with","title":"Interpretable Convolutional Filters with SincNet","date":"2018-11-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/the-pytorch-kaldi-speech-recognition-toolkit","title":"The PyTorch-Kaldi Speech Recognition Toolkit","date":"2018-11-19","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":6,"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."}