mlsanityData to 14 Oct 2026

Fusing ASR Outputs in Joint Training for Speech Emotion Recognition

arXiv 2110.15684 ↗First posted 29 Oct 2021eess.AS cs.CL cs.MMcited by 21

Not on the map. Why?

Abstract (arXiv)

Alongside acoustic information, linguistic features based on speech transcripts have been proven useful in Speech Emotion Recognition (SER). However, due to the scarcity of emotion labelled data and the difficulty of recognizing emotional speech, it is hard to obtain reliable linguistic features and models in this research area. In this paper, we propose to fuse Automatic Speech Recognition (ASR) outputs into the pipeline for joint training SER. The relationship between ASR and SER is understudied, and it is unclear what and how ASR features benefit SER. By examining various ASR outputs and fusion methods, our experiments show that in joint ASR-SER training, incorporating both ASR hidden and text output using a hierarchical co-attention fusion approach improves the SER performance the most. On the IEMOCAP corpus, our approach achieves 63.4% weighted accuracy, which is close to the baseline results achieved by combining ground-truth transcripts. In addition, we also present novel word error rate analysis on IEMOCAP and layer-difference analysis of the Wav2vec 2.0 model to better understand the relationship between ASR and SER.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 8 of its 21 references that are in the map. First posted on arXiv 29 Oct 2021.

Builds on

8 of 21 references.

References · 8

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  4. 2021Layer-wise Analysis of a Self-supervised Speech Representation Modelcited by 298
  5. 2019Learning Problem-agnostic Speech Representations from Multiple Self-supervised Taskscited by 87
  6. 2018Multimodal Speech Emotion Recognition Using Audio and Textcited by 55
  7. 2018ASR-based Features for Emotion Recognition: A Transfer Learning Approachcited by 6
  8. 2020A Transfer Learning Method for Speech Emotion Recognition from Automatic Speech Recognitioncited by 3

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 5; 2024: 9; 2025: 3.

21 papers.

Sort:

  1. 2022Exploration of A Self-Supervised Speech Model: A Study on Emotional Corporacited by 31
  2. 2024Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognitioncited by 11
  3. 2023ASR and Emotional Speech: A Word-Level Investigation of the Mutual Impact of Speech and Emotion Recognitioncited by 7
  4. 2025BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognitioncited by 5
  5. 2023Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representationscited by 4
  6. 2023A Comprehensive Study on the Effectiveness of ASR Representations for Noise-Robust Speech Emotion Recognitioncited by 4
  7. 2024Cross-Lingual Speech Emotion Recognition: Humans vs. Self-Supervised Modelscited by 3
  8. 2024Semi-Supervised Cognitive State Classification from Speech with Multi-View Pseudo-Labelingcited by 3
  9. 2022A Persian ASR-based SER: Modification of Sharif Emotional Speech Database and Investigation of Persian Text Corporacited by 2
  10. 2024Disentangling Textual and Acoustic Features of Neural Speech Representationscited by 2
  11. 2022Multilingual Speech Emotion Recognition With Multi-Gating Mechanism and Neural Architecture Searchcited by 1
  12. 2023Cross-Attention is Not Enough: Incongruity-Aware Dynamic Hierarchical Fusion for Multimodal Affect Recognitioncited by 1
9 more
  1. 2024STAA-Net: A Sparse and Transferable Adversarial Attack for Speech Emotion Recognitioncited by 1
  2. 2024Context and System Fusion in Post-ASR Emotion Recognition with Large Language Modelscited by 1
  3. 2024Improving Speech-based Emotion Recognition with Contextual Utterance Analysis and LLMscited by 1
  4. 2025Developing a High-performance Framework for Speech Emotion Recognition in Naturalistic Conditions Challenge for Emotional Attribute Predictioncited by 1
  5. 2022A Cross-Domain Approach for Continuous Impression Recognition from Dyadic Audio-Visual-Physio Signalscited by 0
  6. 2023On the Efficacy and Noise-Robustness of Jointly Learned Speech Emotion and Automatic Speech Recognitioncited by 0
  7. 2024An Adapter-Based Unified Model for Multiple Spoken Language Processing Taskscited by 0
  8. 2024Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Featurescited by 0
  9. 2025HarmoniFuse: A Component-Selective and Prompt-Adaptive Framework for Multi-Task Speech Language Modelingcited by 0