{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/emo-superb-an-in-depth-look-at-speech-emotion","title":"EMO-SUPERB: An In-depth Look at Speech Emotion Recognition","arxiv_id":"2402.13018","date":"2024-02-20","proceeding":null,"authors":["Haibin Wu","Huang-Cheng Chou","Kai-Wei Chang","Lucas Goncalves","Jiawei Du","Jyh-Shing Roger Jang","Chi-Chun Lee","Hung-Yi Lee"],"abstract":"Speech emotion recognition (SER) is a pivotal technology for human-computer interaction systems. However, 80.77% of SER papers yield results that cannot be reproduced. We develop EMO-SUPERB, short for EMOtion Speech Universal PERformance Benchmark, which aims to enhance open-source initiatives for SER. EMO-SUPERB includes a user-friendly codebase to leverage 15 state-of-the-art speech self-supervised learning models (SSLMs) for exhaustive evaluation across six open-source SER datasets. EMO-SUPERB streamlines result sharing via an online leaderboard, fostering collaboration within a community-driven benchmark and thereby enhancing the development of SER. On average, 2.58% of annotations are annotated using natural language. SER relies on classification models and is unable to process natural languages, leading to the discarding of these valuable annotations. We prompt ChatGPT to mimic annotators, comprehend natural language annotations, and subsequently re-label the data. By utilizing labels generated by ChatGPT, we consistently achieve an average relative gain of 3.08% across all settings.","url_abs":"https://arxiv.org/abs/2402.13018v4","url_pdf":"https://arxiv.org/pdf/2402.13018v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"emo-superb-an-in-depth-look-at-speech-emotion","repo_url":"https://github.com/EMOsuperb/EMO-SUPERB-submission","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-emotion-recognition","task_name":"Speech Emotion Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.13018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13018"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EMOsuperb/EMO-SUPERB-submission","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"96594bd9f92d4736","entry":"SCE_category","repo":"EMOsuperb/EMO-SUPERB-submission","repo_kind":"official","path":"emo-superb/expert.py","file_url":"https://github.com/EMOsuperb/EMO-SUPERB-submission/blob/HEAD/emo-superb/expert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"96594bd9f92d4736"}},{"code_sha256_prefix":"e95dd45c97bd7ccc","entry":"class_balanced_softmax_cross_entropy_with_softtarget","repo":"EMOsuperb/EMO-SUPERB-submission","repo_kind":"official","path":"emo-superb/expert.py","file_url":"https://github.com/EMOsuperb/EMO-SUPERB-submission/blob/HEAD/emo-superb/expert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e95dd45c97bd7ccc"}},{"code_sha256_prefix":"fefc9ff79bdd730c","entry":"collate_fn_padd","repo":"EMOsuperb/EMO-SUPERB-submission","repo_kind":"official","path":"emo-superb/dataset.py","file_url":"https://github.com/EMOsuperb/EMO-SUPERB-submission/blob/HEAD/emo-superb/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fefc9ff79bdd730c"}},{"code_sha256_prefix":"94da8efcd22778fc","entry":"get_norm_stat_for_wav","repo":"EMOsuperb/EMO-SUPERB-submission","repo_kind":"official","path":"emo-superb/dataset.py","file_url":"https://github.com/EMOsuperb/EMO-SUPERB-submission/blob/HEAD/emo-superb/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94da8efcd22778fc"}},{"code_sha256_prefix":"eb28d5d0f63ed885","entry":"softmax_cross_entropy_with_softtarget","repo":"EMOsuperb/EMO-SUPERB-submission","repo_kind":"official","path":"emo-superb/expert.py","file_url":"https://github.com/EMOsuperb/EMO-SUPERB-submission/blob/HEAD/emo-superb/expert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb28d5d0f63ed885"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}