mlsanityData to 7 Oct 2026

MSAC: Multiple Speech Attribute Control Method for Reliable Speech Emotion Recognition

arXiv 2308.04025 ↗First posted 8 Aug 2023cs.SD cs.AI cs.MMcited by 4

Not on the map. Why?

Abstract (arXiv)

Despite notable progress, speech emotion recognition (SER) remains challenging due to the intricate and ambiguous nature of speech emotion, particularly in wild world. While current studies primarily focus on recognition and generalization abilities, our research pioneers an investigation into the reliability of SER methods in the presence of semantic data shifts and explores how to exert fine-grained control over various attributes inherent in speech signals to enhance speech emotion modeling. In this paper, we first introduce MSAC-SERNet, a novel unified SER framework capable of simultaneously handling both single-corpus and cross-corpus SER. Specifically, concentrating exclusively on the speech emotion attribute, a novel CNN-based SER model is presented to extract discriminative emotional representations, guided by additive margin softmax loss. Considering information overlap between various speech attributes, we propose a novel learning paradigm based on correlations of different speech attributes, termed Multiple Speech Attribute Control (MSAC), which empowers the proposed SER model to simultaneously capture fine-grained emotion-related features while mitigating the negative impact of emotion-agnostic representations. Furthermore, we make a first attempt to examine the reliability of the MSAC-SERNet framework using out-of-distribution detection methods. Experiments on both single-corpus and cross-corpus SER scenarios indicate that MSAC-SERNet not only consistently outperforms the baseline in all aspects, but achieves superior performance compared to state-of-the-art SER approaches.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 40 of its 85 references that are in the map. First posted on arXiv 8 Aug 2023.

Builds on

40 of 85 references.

References · 40

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  5. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  8. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 737
  9. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  10. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  11. 2018Additive Margin Softmax for Face Verificationcited by 275
  12. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
28 more
  1. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  2. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  3. 2020FCOS: A simple and strong anchor-free object detectorcited by 171
  4. 2023Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervisioncited by 167
  5. 2022Dawn of the transformer era in speech emotion recognition: closing the valence gapcited by 155
  6. 2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80
  7. 2022Compression of Generative Pre-trained Language Models via Quantizationcited by 79
  8. 2019Out-of-domain Detection for Natural Language Understanding in Dialog Systemscited by 62
  9. 2022DeepStruct: Pretraining of Language Models for Structure Predictioncited by 45
  10. 2021Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learningcited by 42
  11. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  12. 2018Domain Adversarial for Acoustic Emotion Recognitioncited by 25
  13. 2022Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognitioncited by 19
  14. 2019Attention-Augmented End-to-End Multi-Task Learning for Emotion Prediction from Speechcited by 17
  15. 2019Multi-Task Semi-Supervised Adversarial Autoencoding for Speech Emotion Recognitioncited by 15
  16. 2021Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognitioncited by 14
  17. 2022Speaker Normalization for Self-supervised Speech Emotion Recognitioncited by 14
  18. 2021Efficient Speech Emotion Recognition Using Multi-Scale CNN and Attentioncited by 13
  19. 2022Self Supervised Adversarial Domain Adaptation for Cross-Corpus and Cross-Language Speech Emotion Recognitioncited by 13
  20. 2022Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defensecited by 12
  21. 2023HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanismcited by 11
  22. 2021Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Predictioncited by 8
  23. 2022CTL-MTNet: A Novel CapsNet and Transfer Learning-Based Mixed Task Net for the Single-Corpus and Cross-Corpus Speech Emotion Recognitioncited by 8
  24. 2021Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognitioncited by 7
  25. 2022Learning Speech Emotion Representations in the Quaternion Domaincited by 7
  26. 2023DeepLens: Interactive Out-of-distribution Data Detection in NLP Modelscited by 5
  27. 2018Transferable Positive/Negative Speech Emotion Recognition via Class-wise Adversarial Domain Adaptationcited by 4
  28. 2022LMEC: Learnable Multiplicative Absolute Position Embedding Based Conformer for Speech Recognitioncited by 3

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 1.

4 papers.

  1. 2024Takin: A Cohort of Superior Quality Zero-shot Speech Generation Modelscited by 7
  2. 2025ClapFM-EVC: High-Fidelity and Flexible Emotional Voice Conversion with Dual Control from Natural Language and Speechcited by 3
  3. 2024GMP-TL: Gender-augmented Multi-scale Pseudo-label Enhanced Transfer Learning for Speech Emotion Recognitioncited by 2
  4. 2024Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modelingcited by 1