{"url":"/dataset/salmon","name":"SALMon","full_name":null,"description_markdown":"The SALMon dataset and benchmark was introduced in the paper \"[A Suite for Acoustic Language Model Evaluation](https://arxiv.org/abs/2409.07437)\", with the goal of evaluating the modelling abilities of speech language models with regards to different kinds of acoustic elements.\r\n\r\nIt is built of several sub tasks, each task has 200 pairs of recordings - one considered positive and one negative. The positive recording is meant to be a more likely, realistic sample whereas the negative is less likely by some specific means.\r\n\r\nThe sub tasks can be categorised into two main categories: acoustic consistency and semantic-acoustic alignment. In semantic consistency, the positive sample is a real recording and the negative one is with the same spoken content but an acoustic feature (e.g. speaker) changes mid recording. In the alignment sub-task, the positive recording is one where the text matches the acoustic element (e.g sentiment) and the negative is where they don't.\r\n\r\nSee also the [homepage](https://pages.cs.huji.ac.il/adiyoss-lab/salmon/) or [HuggingFace](https://huggingface.co/datasets/slprl/SALMon).","description_withheld":null,"homepage":"https://pages.cs.huji.ac.il/adiyoss-lab/salmon/","introduced_date":"2024-09-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-suite-for-acoustic-language-model","title":"Salmon: A Suite for Acoustic Language Model Evaluation","first_author":"Gallil Maimon","url":null},"license":{"name":"cc-by-nc 4.0","url":"https://spdx.org/licenses/CC-BY-NC-4.0"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Acoustic Modelling","url":"/task/acoustic-modelling","datasets_with_task":"/datasets/task/acoustic-modelling"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SALMon"],"data_loaders":[{"repo":"https://github.com/slp-rl/salmon","url":"https://huggingface.co/datasets/slprl/SALMon","frameworks":["pytorch"]}],"num_papers_in_archive":9,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-modelling-on-salmon","task":"Language Modelling","dataset_variant":"SALMon","rows":10,"metrics":["Sentiment Consistency","Speaker Consistency","Gender Consistency","Background (Domain) Consistency","Background (Random) Consistency","Room Consistency","Sentiment Alignment","Background Alignment"],"first_row_in_archive_order":{"model":"Spirit-LM (Expr.)","paper":"/paper/spirit-lm-interleaved-spoken-and-written","metrics":{"Background (Domain) Consistency":"55.0","Background (Random) Consistency":"64.0","Background Alignment":"59.5","Gender Consistency":"85.0","Room Consistency":"54.5","Sentiment Alignment":"52.0","Sentiment Consistency":"73.5","Speaker Consistency":"81.0"},"code_links":[{"title":"facebookresearch/spiritlm","url":"https://github.com/facebookresearch/spiritlm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/last-language-model-aware-speech-tokenization","title":"LAST: Language Model Aware Speech Tokenization","date":"2024-09-05","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/spirit-lm-interleaved-spoken-and-written","title":"Spirit LM: Interleaved Spoken and Written Language Model","date":"2024-02-08","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/textually-pretrained-speech-language-models","title":"Textually Pretrained Speech Language Models","date":"2023-05-22","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/text-free-prosody-aware-generative-spoken","title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","date":"2021-09-07","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"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."}