English

Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models

Computation and Language 2020-03-06 v2 Machine Learning Audio and Speech Processing

Abstract

In this paper, we propose to use pre-trained features from end-to-end ASR models to solve speech sentiment analysis as a down-stream task. We show that end-to-end ASR features, which integrate both acoustic and text information from speech, achieve promising results. We use RNN with self-attention as the sentiment classifier, which also provides an easy visualization through attention weights to help interpret model predictions. We use well benchmarked IEMOCAP dataset and a new large-scale speech sentiment dataset SWBD-sentiment for evaluation. Our approach improves the-state-of-the-art accuracy on IEMOCAP from 66.6% to 71.7%, and achieves an accuracy of 70.10% on SWBD-sentiment with more than 49,500 utterances.

Keywords

Cite

@article{arxiv.1911.09762,
  title  = {Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models},
  author = {Zhiyun Lu and Liangliang Cao and Yu Zhang and Chung-Cheng Chiu and James Fan},
  journal= {arXiv preprint arXiv:1911.09762},
  year   = {2020}
}
R2 v1 2026-06-23T12:23:57.151Z