mlsanityData to 14 Oct 2026

Pre-Finetuning for Few-Shot Emotional Speech Recognition

arXiv 2302.12921 ↗First posted 24 Feb 2023cs.CL cs.LG cs.SDcited by 4

Not on the map. Why?

Abstract (arXiv)

Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production environments. We view speaker adaptation as a few-shot learning problem and propose investigating transfer learning approaches inspired by recent success with pre-trained models in natural language tasks. We propose pre-finetuning speech models on difficult tasks to distill knowledge into few-shot downstream classification objectives. We pre-finetune Wav2Vec2.0 on every permutation of four multiclass emotional speech recognition corpora and evaluate our pre-finetuned models through 33,600 few-shot fine-tuning trials on the Emotional Speech Dataset.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 22 of its 40 references that are in the map. First posted on arXiv 24 Feb 2023.

Builds on

22 of 40 references.

References · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  6. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  7. 2022Emergent Abilities of Large Language Modelscited by 2,512
  8. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  9. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  10. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  11. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  12. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
10 more
  1. 2021Muppet: Massive Multi-task Representations with Pre-Finetuningcited by 192
  2. 2020Seen and Unseen emotional style transfer for voice conversion with a new emotional speech datasetcited by 121
  3. 2021BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognitioncited by 88
  4. 2023PLACES: Prompting Language Models for Social Conversation Synthesiscited by 72
  5. 2022Data Augmentation for Intent Classification with Off-the-shelf Large Language Modelscited by 49
  6. 2022Weakly Supervised Data Augmentation Through Prompting for Dialogue Understandingcited by 32
  7. 2018Speaker-Invariant Training via Adversarial Learningcited by 23
  8. 2022Label Semantics for Few Shot Named Entity Recognitioncited by 21
  9. 2022Exploring the Role of Task Transferability in Large-Scale Multi-Task Learningcited by 17
  10. 2022Multitask Learning for Low Resource Spoken Language Understandingcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 1.

4 papers.

  1. 2024Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modelingcited by 3
  2. 2023Towards Generalizable SER: Soft Labeling and Data Augmentation for Modeling Temporal Emotion Shifts in Large-Scale Multilingual Speechcited by 2
  3. 2025More Similar than Dissimilar: Modeling Annotators for Cross-Corpus Speech Emotion Recognitioncited by 2
  4. 2024Active Learning with Task Adaptation Pre-training for Speech Emotion Recognitioncited by 0