English

Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition

Computation and Language 2022-01-31 v1 Sound Audio and Speech Processing

Abstract

We propose a novel multi-task pre-training method for Speech Emotion Recognition (SER). We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more ``emotion aware''. We generate targets for the sentiment classification using text-to-sentiment model trained on publicly available data. Finally, we fine-tune the acoustic ASR on emotion annotated speech data. We evaluated the proposed approach on the MSP-Podcast dataset, where we achieved the best reported concordance correlation coefficient (CCC) of 0.41 for valence prediction.

Keywords

Cite

@article{arxiv.2201.11826,
  title  = {Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition},
  author = {Ayoub Ghriss and Bo Yang and Viktor Rozgic and Elizabeth Shriberg and Chao Wang},
  journal= {arXiv preprint arXiv:2201.11826},
  year   = {2022}
}

Comments

ICASSP 2022

R2 v1 2026-06-24T09:06:22.899Z