Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction
This work addresses the reliability of LLM-based emotion recognition for speech processing applications, though it appears incremental in refining existing prompting methods.
The paper tackled the problem of improving emotion recognition from speech using LLMs by proposing emotion-specific prompts and an ASR error correction pipeline, achieving enhanced efficacy as demonstrated in experiments.
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.