arXiv 2505.162122025-05-24cs.CLeess.AS

基于大语言模型的儿童对话语音识别纠错

Large Language Models based ASR Error Correction for Child Conversations

University of Southern California（美国南加州大学）；Korea University（韩国大学）；University of California, San Francisco（旧金山大学）；University of California, Los Angeles（洛杉矶大学）；Viterbi School of Engineering（工程学院）；School of Psychology（心理学系）；Weill Institute for Neurosciences（神经科学研究所）；Semel Institute of Neuroscience and Human Behavior（神经科学与人类行为研究所）

Anfeng Xu, Tiantian Feng, So Hyun Kim, Somer Bishop, Catherine Lord, Shrikanth Narayanan

备注：: Accepted to Interspeech 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究探索利用大语言模型纠正儿童对话语音识别错误，实验显示其对零样本和CTC输出有效，但对上下文或自回归输出提升有限。

摘要：

自动语音识别（ASR）近年来取得了显著进展，但准确转录儿童语音仍是一项重大挑战。大语言模型（LLMs）的最新发展在改进ASR转录方面展现出潜力，然而其在儿童语音（包括对话场景）中的应用尚未得到充分探索。在本研究中，我们探讨了利用LLMs纠正对话式儿童语音中ASR错误的方法。我们通过在两个儿童对话语音数据集上进行实验，使用零样本和微调后的ASR输出，展示了LLMs的潜力和挑战。我们发现，虽然LLMs在纠正零样本ASR输出和基于微调CTC的ASR输出方面有所帮助，但在整合上下文信息或使用微调自回归ASR（如Whisper）输出时，LLMs提升ASR性能仍具挑战性。

英文摘要：

Automatic Speech Recognition (ASR) has recently shown remarkable progress, but accurately transcribing children's speech remains a significant challenge. Recent developments in Large Language Models (LLMs) have shown promise in improving ASR transcriptions. However, their applications in child speech including conversational scenarios are underexplored. In this study, we explore the use of LLMs in correcting ASR errors for conversational child speech. We demonstrate the promises and challenges of LLMs through experiments on two children's conversational speech datasets with both zero-shot and fine-tuned ASR outputs. We find that while LLMs are helpful in correcting zero-shot ASR outputs and fine-tuned CTC-based ASR outputs, it remains challenging for LLMs to improve ASR performance when incorporating contextual information or when using fine-tuned autoregressive ASR (e.g., Whisper) outputs.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。