Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yuanchao, Gong, Yuan, Yang, Chao-Han Huck, Bell, Peter, Lai, Catherine
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915266144763904
author Li, Yuanchao
Gong, Yuan
Yang, Chao-Han Huck
Bell, Peter
Lai, Catherine
author_facet Li, Yuanchao
Gong, Yuan
Yang, Chao-Han Huck
Bell, Peter
Lai, Catherine
contents Annotating and recognizing speech emotion using prompt engineering has recently emerged with the advancement of Large Language Models (LLMs), yet its efficacy and reliability remain questionable. In this paper, we conduct a systematic study on this topic, beginning with the proposal of novel prompts that incorporate emotion-specific knowledge from acoustics, linguistics, and psychology. Subsequently, we examine the effectiveness of LLM-based prompting on Automatic Speech Recognition (ASR) transcription, contrasting it with ground-truth transcription. Furthermore, we propose a Revise-Reason-Recognize prompting pipeline for robust LLM-based emotion recognition from spoken language with ASR errors. Additionally, experiments on context-aware learning, in-context learning, and instruction tuning are performed to examine the usefulness of LLM training schemes in this direction. Finally, we investigate the sensitivity of LLMs to minor prompt variations. Experimental results demonstrate the efficacy of the emotion-specific prompts, ASR error correction, and LLM training schemes for LLM-based emotion recognition. Our study aims to refine the use of LLMs in emotion recognition and related domains.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15551
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction
Li, Yuanchao
Gong, Yuan
Yang, Chao-Han Huck
Bell, Peter
Lai, Catherine
Audio and Speech Processing
Artificial Intelligence
Computation and Language
Multimedia
Sound
Annotating and recognizing speech emotion using prompt engineering has recently emerged with the advancement of Large Language Models (LLMs), yet its efficacy and reliability remain questionable. In this paper, we conduct a systematic study on this topic, beginning with the proposal of novel prompts that incorporate emotion-specific knowledge from acoustics, linguistics, and psychology. Subsequently, we examine the effectiveness of LLM-based prompting on Automatic Speech Recognition (ASR) transcription, contrasting it with ground-truth transcription. Furthermore, we propose a Revise-Reason-Recognize prompting pipeline for robust LLM-based emotion recognition from spoken language with ASR errors. Additionally, experiments on context-aware learning, in-context learning, and instruction tuning are performed to examine the usefulness of LLM training schemes in this direction. Finally, we investigate the sensitivity of LLMs to minor prompt variations. Experimental results demonstrate the efficacy of the emotion-specific prompts, ASR error correction, and LLM training schemes for LLM-based emotion recognition. Our study aims to refine the use of LLMs in emotion recognition and related domains.
title Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction
topic Audio and Speech Processing
Artificial Intelligence
Computation and Language
Multimedia
Sound
url https://arxiv.org/abs/2409.15551