用特定情绪提示和纠错提升语音情感识别准确率
Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction
- 设计情绪特异性提示，融合声学语言学心理学知识
- 结合ASR纠错与三阶段推理流程，显著提升识别效果
- 验证提示微调对模型敏感性的影响，适合语音情感研究者
随着大语言模型（LLMs）的发展，基于提示工程的语音情感标注与识别逐渐兴起，但其有效性与可靠性仍存疑。本文系统研究该方向，首先提出融合声学、语言学与心理学情绪知识的情绪特异性提示。接着对比了基于LLM提示的自动语音识别（ASR）转录与真实转录的效果。进一步提出“修订-推理-识别”三阶段提示流程，以应对含错的语音转录，增强情感识别鲁棒性。实验还考察了上下文学习、提示学习与指令微调等训练策略的有效性，并分析了提示细微变化对LLM性能的影响。结果表明，情绪特异性提示、ASR错误纠正及合适的训练方案能显著提升基于LLM的情感识别性能。本研究旨在优化LLM在情感识别及相关领域的应用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。