{"url":"/dataset/dusha","name":"Dusha","full_name":"Dusha Crowd, Dusha Podcast","description_markdown":"**Dusha** is a dataset for speech emotion recognition (SER) tasks. The corpus contains approximately 350 hours of data, more than 300 000 audio recordings with Russian speech and their transcripts. It is annotated using a crowd-sourcing platform and includes two subsets: acted and real-life.\r\n\r\nSource: [Large Raw Emotional Dataset with Aggregation Mechanism](https://arxiv.org/pdf/2212.12266v1.pdf)","description_withheld":null,"homepage":"https://github.com/salute-developers/golos/tree/master/dusha#dusha-dataset","introduced_date":"2022-12-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/large-raw-emotional-dataset-with-aggregation","title":"Large Raw Emotional Dataset with Aggregation Mechanism","first_author":"Vladimir Kondratenko","url":null},"license":{"name":"Custom","url":"https://github.com/salute-developers/golos/blob/master/license/en_us.pdf"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Emotion Recognition","url":"/task/emotion-recognition","datasets_with_task":"/datasets/task/emotion-recognition"},{"name":"Speech Emotion Recognition","url":"/task/speech-emotion-recognition","datasets_with_task":"/datasets/task/speech-emotion-recognition"}],"languages":[{"name":"Russian","url":"/datasets/language/russian"}],"variants":["Dusha","Dusha Crowd","Dusha Podcast"],"data_loaders":[{"repo":"https://github.com/salute-developers/golos","url":"https://github.com/salute-developers/golos","frameworks":[]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-emotion-recognition-on-dusha-crowd","task":"Speech Emotion Recognition","dataset_variant":"Dusha Crowd","rows":1,"metrics":["Macro F1","UA","WA"],"first_row_in_archive_order":{"model":"Dusha baseline","paper":"/paper/large-raw-emotional-dataset-with-aggregation","metrics":{"Macro F1":"0.77","UA":"0.83","WA":"0.76"},"code_links":[{"title":"salute-developers/golos","url":"https://github.com/salute-developers/golos"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-emotion-recognition-on-dusha-podcast","task":"Speech Emotion Recognition","dataset_variant":"Dusha Podcast","rows":1,"metrics":["Macro F1","UA","WA"],"first_row_in_archive_order":{"model":"Dusha baseline","paper":"/paper/large-raw-emotional-dataset-with-aggregation","metrics":{"Macro F1":"0.54","UA":"0.89","WA":"0.53"},"code_links":[{"title":"salute-developers/golos","url":"https://github.com/salute-developers/golos"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/large-raw-emotional-dataset-with-aggregation","title":"Large Raw Emotional Dataset with Aggregation Mechanism","date":"2022-12-23","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"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":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"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."}