mlsanityData to 7 Oct 2026

Self-Supervised Attention Networks and Uncertainty Loss Weighting for Multi-Task Emotion Recognition on Vocal Bursts

arXiv 2209.07384 ↗First posted 15 Sep 2022cs.SD cs.AI eess.AScited by 1

Not on the map. Why?

Abstract (arXiv)

Vocal bursts play an important role in communicating affect, making them valuable for improving speech emotion recognition. Here, we present our approach for classifying vocal bursts and predicting their emotional significance in the ACII Affective Vocal Burst Workshop & Challenge 2022 (A-VB). We use a large self-supervised audio model as shared feature extractor and compare multiple architectures built on classifier chains and attention networks, combined with uncertainty loss weighting strategies. Our approach surpasses the challenge baseline by a wide margin on all four tasks.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 13 of its 25 references that are in the map. First posted on arXiv 15 Sep 2022.

Builds on

13 of 25 references.

References · 13

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  2. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  3. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  4. 2021Emotion Recognition from Speech Using Wav2vec 2.0 Embeddingscited by 158
  5. 2022Dawn of the transformer era in speech emotion recognition: closing the valence gapcited by 155
  6. 2018Auxiliary Tasks in Multi-task Learningcited by 106
  7. 2022The ICML 2022 Expressive Vocalizations Workshop and Competition: Recognizing, Generating, and Personalizing Vocal Burstscited by 16
  8. 2022The ACII 2022 Affective Vocal Bursts Workshop & Competition: Understanding a critically understudied modality of emotional expressioncited by 7
  9. 2022Exploring the Effectiveness of Self-supervised Learning and Classifier Chains in Emotion Recognition of Nonverbal Vocalizationscited by 5
  10. 2022Redundancy Reduction Twins Network: A Training framework for Multi-output Emotion Regressioncited by 4
  11. 2022Exploring speaker enrolment for few-shot personalisation in emotional vocalisation predictioncited by 3
  12. 2022Dynamic Restrained Uncertainty Weighting Loss for Multitask Learning of Vocal Expressioncited by 2
1 more
  1. 2022Jointly Predicting Emotion, Age, and Country Using Pre-Trained Acoustic Embeddingcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024The NeurIPS 2023 Machine Learning for Audio Workshop: Affective Audio Benchmarks and Novel Datacited by 0