SOTAVerified

Speech Emotion Recognition

Speech Emotion Recognition is a task of speech processing and computational paralinguistics that aims to recognize and categorize the emotions expressed in spoken language. The goal is to determine the emotional state of a speaker, such as happiness, anger, sadness, or frustration, from their speech patterns, such as prosody, pitch, and rhythm.

For multimodal emotion recognition, please upload your result to Multimodal Emotion Recognition on IEMOCAP

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 431 papers

TitleStatusHype
Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in ConversationCode0
MATER: Multi-level Acoustic and Textual Emotion Representation for Interpretable Speech Emotion Recognition—0
Developing a High-performance Framework for Speech Emotion Recognition in Naturalistic Conditions Challenge for Emotional Attribute Prediction—0
MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic ConditionsCode0
Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion RecognitionCode0
CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition—0
EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition—0
HYFuse: Aligning Heterogeneous Speech Pre-Trained Representations in Hyperbolic Space for Speech Emotion Recognition—0
Investigating the Impact of Word Informativeness on Speech Emotion Recognition—0
Are Mamba-based Audio Foundation Models the Best Fit for Non-Verbal Emotion Recognition?—0
Towards Machine Unlearning for Paralinguistic Speech Processing—0
Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025—0
Learning More with Less: Self-Supervised Approaches for Low-Resource Speech Emotion Recognition—0
Source Tracing of Synthetic Speech Systems Through Paralinguistic Pre-Trained Representations—0
PARROT: Synergizing Mamba and Attention-based SSL Pre-Trained Models via Parallel Branch Hadamard Optimal Transport for Speech Emotion Recognition—0
MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded KnowledgeCode0
Can Emotion Fool Anti-spoofing?—0
EmoSphere-SER: Enhancing Speech Emotion Recognition Through Spherical Representation with Auxiliary ClassificationCode2
Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking ModelCode0
ABHINAYA -- A System for Speech Emotion Recognition In Naturalistic Conditions ChallengeCode0
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingCode11
Meta-PerSER: Few-Shot Listener Personalized Speech Emotion Recognition via Meta-learning—0
Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach—0
CAMEO: Collection of Multilingual Emotional Speech Corpora—0
Empirical Analysis of Asynchronous Federated Learning on Heterogeneous Devices: Efficiency, Fairness, and Privacy Trade-offs—0
BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech RecognitionCode0
Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across LanguagesCode0
Deep Learning for Speech Emotion Recognition: A CNN Approach Utilizing Mel Spectrograms—0
Coverage-Guaranteed Speech Emotion Recognition via Calibrated Uncertainty-Adaptive Prediction Sets—0
Heterogeneous bimodal attention fusion for speech emotion recognition—0
Bimodal Connection Attention Fusion for Speech Emotion Recognition—0
Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of ThoughtCode1
SigWavNet: Learning Multiresolution Signal Wavelet Network for Speech Emotion RecognitionCode1
OSUM: Advancing Open Speech Understanding Models with Limited Resources in AcademiaCode3
EmoTech: A Multi-modal Speech Emotion Recognition Using Multi-source Low-level Information with Hybrid Recurrent Network—0
EmoFormer: A Text-Independent Speech Emotion Recognition using a Hybrid Transformer-CNN model—0
Representation Learning with Parameterised Quantum Circuits for Advancing Speech Emotion Recognition—0
Leveraging Cross-Attention Transformer and Multi-Feature Fusion for Cross-Linguistic Speech Emotion Recognition—0
learning discriminative features from spectrograms using center loss for speech emotion recognition—0
Is It Still Fair? Investigating Gender Fairness in Cross-Corpus Speech Emotion Recognition—0
Metadata-Enhanced Speech Emotion Recognition: Augmented Residual Integration and Co-Attention in Two-Stage Fine-Tuning—0
Mouth Articulation-Based Anchoring for Improved Cross-Corpus Speech Emotion Recognition—0
Enhanced Speech Emotion Recognition with Efficient Channel Attention Guided Deep CNN-BiLSTM Framework—0
Emotional Vietnamese Speech-Based Depression Diagnosis Using Dynamic Attention MechanismCode0
WavFusion: Towards wav2vec 2.0 Multimodal Speech Emotion Recognition—0
A Cross-Corpus Speech Emotion Recognition Method Based on Supervised Contrastive Learning—0
Once More, With Feeling: Measuring Emotion of Acting Performances in Contemporary American Film—0
Re-Parameterization of Lightweight Transformer for On-Device Speech Emotion Recognition—0
Improvement and Implementation of a Speech Emotion Recognition Model Based on Dual-Layer LSTM—0
Multi-modal Speech Emotion Recognition via Feature Distribution Adaptation NetworkCode0
Show:102550
← PrevPage 1 of 9Next →
All datasetsCREMA-DIEMOCAPRAVDESSMSP-Podcast (Activation)MSP-Podcast (Dominance)MSP-Podcast (Valence)BERStRESDDusha CrowdDusha PodcastEMODBEmoDB Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Vertically long patch ViTAccuracy94.07—Unverified
2ConformerXL-PAccuracy88.2—Unverified
3CoordViTAccuracy82.96—Unverified
4SepTr + LeRaCAccuracy70.95—Unverified
5SepTrAccuracy70.47—Unverified
6ResNet-18 + SPELAccuracy68.12—Unverified
7ViTAccuracy67.81—Unverified
8ResNet-18 + PyNADAAccuracy65.15—Unverified
9GRUAccuracy55.01—Unverified
#ModelMetricClaimedVerifiedStatus
1SER with MTLUA CV0.78—Unverified
2emoDARTSUA CV0.77—Unverified
3LSTM+FCWA0.76—Unverified
4TAPWA CV0.74—Unverified
5SYSCOMB: BLSTMATT with CSA (session5)UA0.74—Unverified
6Partially Fine-tuned HuBERT LargeWA CV0.73—Unverified
7CNN - DARTSUA0.7—Unverified
8CNN+LSTMUA0.65—Unverified
#ModelMetricClaimedVerifiedStatus
1VQ-MAE-S-12 (Frame) + Query2EmoAccuracy84.1—Unverified
2CNN-X (Shallow CNN)Accuracy82.99—Unverified
3xlsr-Wav2Vec2.0(FineTuning)Accuracy81.82—Unverified
4CNN-14 (Fine-Tuning)Accuracy76.58—Unverified
5AlexNet (FineTuning)Accuracy61.67—Unverified
#ModelMetricClaimedVerifiedStatus
1wav2small-TeacherCCC0.76—Unverified
2wavlmCCC0.75—Unverified
3w2v2-L-robust-12CCC0.75—Unverified
4preCPCCCC0.71—Unverified
#ModelMetricClaimedVerifiedStatus
1wav2small-TeacherCCC0.68—Unverified
2wavlmCCC0.67—Unverified
3w2v2-L-robust-12CCC0.66—Unverified
4preCPCCCC0.64—Unverified
#ModelMetricClaimedVerifiedStatus
1wav2small-TeacherCCC0.68—Unverified
2wavlmCCC0.65—Unverified
3w2v2-L-robust-12CCC0.64—Unverified
4preCPCCCC0.38—Unverified
#ModelMetricClaimedVerifiedStatus
1DAWN-hidden-SVMUnweighted Accuracy (UA)32.1—Unverified
2Wav2Small-VAD-SVMUnweighted Accuracy (UA)23.3—Unverified
3Speechbrain Wav2Vec2Unweighted Accuracy (UA)20.7—Unverified
#ModelMetricClaimedVerifiedStatus
1emotion2vec+baseWeighted Accuracy (WA)79.4—Unverified
2emotion2vec+largeWeighted Accuracy (WA)69.5—Unverified
3emotion2vecWeighted Accuracy (WA)64.75—Unverified
#ModelMetricClaimedVerifiedStatus
1Dusha baselineMacro F10.77—Unverified
#ModelMetricClaimedVerifiedStatus
1Dusha baselineMacro F10.54—Unverified
#ModelMetricClaimedVerifiedStatus
1VGG-optiVMD1:1 Accuracy96.09—Unverified
#ModelMetricClaimedVerifiedStatus
1VQ-MAE-S-12 (Frame) + Query2EmoAccuracy90.2—Unverified
#ModelMetricClaimedVerifiedStatus
1PyResNetUnweighted Accuracy (UA)0.43—Unverified
#ModelMetricClaimedVerifiedStatus
1emoDARTSUA0.66—Unverified
#ModelMetricClaimedVerifiedStatus
1LSTMCCC (Arousal)0.76—Unverified
#ModelMetricClaimedVerifiedStatus
1CNN (1D)Unweighted Accuracy65.2—Unverified