ASR error correction is an interesting option for post processing speech recognition system outputs. These error correction models are usually trained in a supervised fashion using the decoding results of a target ASR system. This approach can be computationally intensive and the model is tuned to a specific ASR system. Recently generative large language models (LLMs) have been applied to a wide range of natural language processing tasks, as they can operate in a zero-shot or few shot fashion. In this paper we investigate using ChatGPT, a generative LLM, for ASR error correction. Based on the ASR N-best output, we propose both unconstrained and constrained, where a member of the N-best list is selected, approaches. Additionally, zero and 1-shot settings are evaluated. Experiments show that this generative LLM approach can yield performance gains for two different state-of-the-art ASR architectures, transducer and attention-encoder-decoder based, and multiple test sets.

翻译：ASR错误校正是对语音识别系统输出进行后处理的一种有趣选择。这些错误校正模型通常以有监督的方式训练，使用目标ASR系统的解码结果。该方法计算密集且模型针对特定ASR系统进行调优。近年来，生成式大语言模型（LLMs）已应用于广泛的自然语言处理任务，因为它们可以以零样本或少样本方式运行。本文研究了使用生成式LLM（ChatGPT）进行ASR错误校正。基于ASR的N最佳候选输出，我们提出了无约束和约束两种方法，其中约束方法会从N最佳候选列表中选择一个元素。此外，评估了零样本和一样本设置。实验表明，这种生成式LLM方法能为两种不同的最先进ASR架构（基于转录器和基于注意力-编码器-解码器）以及多个测试集带来性能提升。