mlsanityData to 14 Oct 2026

Speaker Normalization for Self-supervised Speech Emotion Recognition

arXiv 2202.01252 ↗First posted 2 Feb 2022cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts usually harm a model's ability to generalize. To address this challenge, we propose a gradient-based adversary learning framework that learns a speech emotion recognition task while normalizing speaker characteristics from the feature representation. We demonstrate the efficacy of our method on both speaker-independent and speaker-dependent settings and obtain new state-of-the-art results on the challenging IEMOCAP dataset.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 2 Feb 2022.

Builds on

18 of 31 references.

References · 18

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  5. 2017VoxCeleb: a large-scale speaker identification datasetcited by 732
  6. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 666
  7. 2019Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoderscited by 198
  8. 2020TERA: Self-Supervised Learning of Transformer Encoder Representation for Speechcited by 188
  9. 2019An Unsupervised Autoregressive Model for Speech Representation Learningcited by 186
  10. 2021Emotion Recognition from Speech Using Wav2vec 2.0 Embeddingscited by 162
  11. 2020Unsupervised pretraining transfers well across languagescited by 101
  12. 2020Vector-Quantized Autoregressive Predictive Codingcited by 69
6 more
  1. 2018Multimodal Speech Emotion Recognition Using Audio and Textcited by 55
  2. 2020Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependenciescited by 47
  3. 2020Disentangled Speech Embeddings using Cross-modal Self-supervisioncited by 30
  4. 2019Speech Emotion Recognition with Dual-Sequence LSTM Architecturecited by 23
  5. 2016Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Datacited by 17
  6. 2021Speaker Attentive Speech Emotion Recognitioncited by 9

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 8; 2024: 4.

14 papers.

Sort:

  1. 2023Speech Emotion Diarization: Which Emotion Appears When?cited by 13
  2. 2023Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognitioncited by 12
  3. 2023GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognitioncited by 10
  4. 2022Topological Data Analysis for Speech Processingcited by 9
  5. 2023Designing and Evaluating Speech Emotion Recognition Systems: A reality check case study with IEMOCAPcited by 6
  6. 2024MFHCA: Enhancing Speech Emotion Recognition Via Multi-Spatial Fusion and Hierarchical Cooperative Attentioncited by 6
  7. 2023MSAC: Multiple Speech Attribute Control Method for Reliable Speech Emotion Recognitioncited by 4
  8. 2022Speech Emotion Recognition via an Attentive Time-Frequency Neural Networkcited by 3
  9. 2024Parameter Efficient Finetuning for Speech Emotion Recognition and Domain Adaptationcited by 3
  10. 2023Frame-level emotional state alignment method for speech emotion recognitioncited by 2
  11. 2024GMP-TL: Gender-augmented Multi-scale Pseudo-label Enhanced Transfer Learning for Speech Emotion Recognitioncited by 2
  12. 2023Adversarial Speaker Disentanglement Using Unannotated External Data for Self-supervised Representation Based Voice Conversioncited by 1
2 more
  1. 2023DSNet: Disentangled Siamese Network with Neutral Calibration for Speech Emotion Recognitioncited by 1
  2. 2024Investigating Acoustic-Textual Emotional Inconsistency Information for Automatic Depression Detectioncited by 1