Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition (2025)
Emotion-Qwen: Training Hybrid Experts for Unified Emotion and General Vision-Language Understanding (2025)
EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations (2025)
VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection (2025)
Can Emotion Fool Anti-spoofing? (2025)
EmoSign: A Multimodal Dataset for Understanding Emotions in American Sign Language (2025)
EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast (2025)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2025-06-21T01:34:32.148Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":264}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.6849551200866699},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2506.09827","authors":[{"_id":"685519bb4f1add9d4c5c5cbd","user":{"_id":"61a24fc72101184cfb29c965","avatarUrl":"/avatars/e32aa61016caef50de28c16b30196799.svg","isPro":false,"fullname":"Christoph Schuhmann","user":"ChristophSchuhmann","type":"user"},"name":"Christoph Schuhmann","status":"extracted_confirmed","statusLastChangedAt":"2025-06-20T10:22:26.676Z","hidden":false},{"_id":"685519bb4f1add9d4c5c5cbe","name":"Robert Kaczmarczyk","hidden":false},{"_id":"685519bb4f1add9d4c5c5cbf","user":{"_id":"64ac21f11cacea8d4b8f2b3f","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64ac21f11cacea8d4b8f2b3f/asQOf8wFZ4vmqIeyxfvUR.jpeg","isPro":false,"fullname":"Gollam Rabby","user":"tourist800","type":"user"},"name":"Gollam Rabby","status":"admin_assigned","statusLastChangedAt":"2025-06-20T12:29:47.779Z","hidden":false},{"_id":"685519bb4f1add9d4c5c5cc0","user":{"_id":"62e7dd4036a8e8a82700041c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62e7dd4036a8e8a82700041c/Dgk9mXYLVd4LpiNLWjn-q.jpeg","isPro":false,"fullname":"Felix Friedrich","user":"felfri","type":"user"},"name":"Felix Friedrich","status":"claimed_verified","statusLastChangedAt":"2025-06-20T08:57:36.090Z","hidden":false},{"_id":"685519bb4f1add9d4c5c5cc1","name":"Maurice Kraus","hidden":false},{"_id":"685519bb4f1add9d4c5c5cc2","name":"Kourosh Nadi","hidden":false},{"_id":"685519bb4f1add9d4c5c5cc3","user":{"_id":"5fc6879e1c5ee87b1164876d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5fc6879e1c5ee87b1164876d/Tjnm_lv0Bq0gPbFOTDH6E.jpeg","isPro":false,"fullname":"Huu Nguyen","user":"huu-ontocord","type":"user"},"name":"Huu Nguyen","status":"claimed_verified","statusLastChangedAt":"2025-06-23T08:15:57.375Z","hidden":false},{"_id":"685519bb4f1add9d4c5c5cc4","name":"Kristian Kersting","hidden":false},{"_id":"685519bb4f1add9d4c5c5cc5","user":{"_id":"62cd8f74342b1d5dab8da3a6","avatarUrl":"/avatars/51c237653aadc98c73df207d9d054597.svg","isPro":false,"fullname":"Sören Auer","user":"soeren1611","type":"user"},"name":"Sören Auer","status":"admin_assigned","statusLastChangedAt":"2025-06-20T12:30:06.624Z","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/62e7dd4036a8e8a82700041c/tvkMYrIKiGhbIVAuaxvlt.png"],"publishedAt":"2025-06-11T15:06:59.000Z","submittedOnDailyAt":"2025-06-20T06:53:47.262Z","title":"EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech\n Emotion Detection","submittedOnDailyBy":{"_id":"62e7dd4036a8e8a82700041c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62e7dd4036a8e8a82700041c/Dgk9mXYLVd4LpiNLWjn-q.jpeg","isPro":false,"fullname":"Felix Friedrich","user":"felfri","type":"user"},"summary":"The advancement of text-to-speech and audio generation models necessitates\nrobust benchmarks for evaluating the emotional understanding capabilities of AI\nsystems. Current speech emotion recognition (SER) datasets often exhibit\nlimitations in emotional granularity, privacy concerns, or reliance on acted\nportrayals. This paper introduces EmoNet-Voice, a new resource for speech\nemotion detection, which includes EmoNet-Voice Big, a large-scale pre-training\ndataset (featuring over 4,500 hours of speech across 11 voices, 40 emotions,\nand 4 languages), and EmoNet-Voice Bench, a novel benchmark dataset with human\nexpert annotations. EmoNet-Voice is designed to evaluate SER models on a\nfine-grained spectrum of 40 emotion categories with different levels of\nintensities. Leveraging state-of-the-art voice generation, we curated synthetic\naudio snippets simulating actors portraying scenes designed to evoke specific\nemotions. Crucially, we conducted rigorous validation by psychology experts who\nassigned perceived intensity labels. This synthetic, privacy-preserving\napproach allows for the inclusion of sensitive emotional states often absent in\nexisting datasets. Lastly, we introduce Empathic Insight Voice models that set\na new standard in speech emotion recognition with high agreement with human\nexperts. Our evaluations across the current model landscape exhibit valuable\nfindings, such as high-arousal emotions like anger being much easier to detect\nthan low-arousal states like concentration.","upvotes":18,"discussionId":"685519bb4f1add9d4c5c5cc6","ai_summary":"EmoNet-Voice, a new resource with large pre-training and benchmark datasets, advances speech emotion recognition by offering fine-grained emotion evaluation with synthetic, privacy-preserving audio.","ai_keywords":["speech emotion recognition","SER","EmoNet-Voice","EmoNet-Voice Big","EmoNet-Voice Bench","human expert annotations","synthetic audio snippets","psychology experts","high-arousal emotions","low-arousal states","Empathic Insight Voice models"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"62e7dd4036a8e8a82700041c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62e7dd4036a8e8a82700041c/Dgk9mXYLVd4LpiNLWjn-q.jpeg","isPro":false,"fullname":"Felix Friedrich","user":"felfri","type":"user"},{"_id":"635ba0c637c6a2c12e2daef9","avatarUrl":"/avatars/9fc2932d9ace2715f540f896754ec7d2.svg","isPro":false,"fullname":"Ollie McCarthy","user":"ollieollie","type":"user"},{"_id":"648eb1eb59c4e5c87dc116e0","avatarUrl":"/avatars/c636cea39c2c0937f01398c94ead5dad.svg","isPro":false,"fullname":"fdsqefsgergd","user":"T-representer","type":"user"},{"_id":"64273c8c5bca6f17a3187617","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/YbUO2zchO3ZTL2hViKzlQ.jpeg","isPro":false,"fullname":"Luan Dopke","user":"luandopke","type":"user"},{"_id":"61fc3f7a87117e8015dd1166","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61fc3f7a87117e8015dd1166/v8D6S9bh0BS88BHajQPb6.png","isPro":false,"fullname":"Marian Basti","user":"marianbasti","type":"user"},{"_id":"665b133508d536a8ac804f7d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/Uwi0OnANdTbRbHHQvGqvR.png","isPro":false,"fullname":"Paulson","user":"Pnaomi","type":"user"},{"_id":"62e54f0eae9d3f10acb95cb9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62e54f0eae9d3f10acb95cb9/VAyk05hqB3OZWXEZW-B0q.png","isPro":true,"fullname":"mrfakename","user":"mrfakename","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"63e749fbe02ee67e8e4e9101","avatarUrl":"/avatars/8b4406f5831df17eccb9bf18a97afb90.svg","isPro":false,"fullname":"Jeff Gao","user":"jeff-gao","type":"user"},{"_id":"67a3446691b7a8e1b11c1cb7","avatarUrl":"/avatars/46e7d3629d81d1b231f1df7bf6eef273.svg","isPro":false,"fullname":"Umair Abbas","user":"mianumairsiddiquie","type":"user"},{"_id":"66f85f4ab720048bbc5487e1","avatarUrl":"/avatars/384196d5676e9c8d8970e5b84914e328.svg","isPro":false,"fullname":"Ali Ihsan Nergiz","user":"nergizai","type":"user"},{"_id":"5fc6879e1c5ee87b1164876d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5fc6879e1c5ee87b1164876d/Tjnm_lv0Bq0gPbFOTDH6E.jpeg","isPro":false,"fullname":"Huu Nguyen","user":"huu-ontocord","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":3}">

Papers

arxiv:2506.09827

EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection

Published on Jun 11

· Submitted by

Felix Friedrich on Jun 20

#3 Paper of the day

Upvote

Authors:

Christoph Schuhmann ,

Gollam Rabby ,

Felix Friedrich ,

Huu Nguyen ,

Sören Auer

Abstract

EmoNet-Voice, a new resource with large pre-training and benchmark datasets, advances speech emotion recognition by offering fine-grained emotion evaluation with synthetic, privacy-preserving audio.

AI-generated summary

The advancement of text-to-speech and audio generation models necessitates robust benchmarks for evaluating the emotional understanding capabilities of AI systems. Current speech emotion recognition (SER) datasets often exhibit limitations in emotional granularity, privacy concerns, or reliance on acted portrayals. This paper introduces EmoNet-Voice, a new resource for speech emotion detection, which includes EmoNet-Voice Big, a large-scale pre-training dataset (featuring over 4,500 hours of speech across 11 voices, 40 emotions, and 4 languages), and EmoNet-Voice Bench, a novel benchmark dataset with human expert annotations. EmoNet-Voice is designed to evaluate SER models on a fine-grained spectrum of 40 emotion categories with different levels of intensities. Leveraging state-of-the-art voice generation, we curated synthetic audio snippets simulating actors portraying scenes designed to evoke specific emotions. Crucially, we conducted rigorous validation by psychology experts who assigned perceived intensity labels. This synthetic, privacy-preserving approach allows for the inclusion of sensitive emotional states often absent in existing datasets. Lastly, we introduce Empathic Insight Voice models that set a new standard in speech emotion recognition with high agreement with human experts. Our evaluations across the current model landscape exhibit valuable findings, such as high-arousal emotions like anger being much easier to detect than low-arousal states like concentration.

View arXiv page View PDF Add to collection

Community

felfri

Paper author Paper submitter Jun 20

Do They Hear What We Hear?

An exciting frontier in technology today is the quest for artificial intelligence that truly understands and interacts with humans on a deeper level. While AI has made remarkable progress in language processing and complex problem-solving, one critical dimension has yet to be fully realized: true emotional intelligence.

Can our AI systems perceive the subtle joy in a crinkled eye, the faint tremor of anxiety in a voice, or the complex blend of emotions that color our everyday interactions? We believe this is not just a fascinating academic pursuit but a fundamental necessity for the future of human-AI collaboration.

Today, we're proud to release EmoNet – a suite of new, open and freely available models and tools designed to support global research and innovation in the emerging field of emotionally intelligent AI. Our contributions are multi-faceted, addressing critical gaps in current research and providing powerful new tools for the global AI community.