This paper proposes an automatic speech recognition (ASR) model for hate speech using large language models (LLMs). The proposed method integrates the encoder of the ASR model with the decoder of the LLMs, enabling simultaneous transcription and censorship tasks to prevent the exposure of harmful content. Instruction tuning of the LLM to mask hate-related words with specific tokens requires an annotated hate speech dataset, which is limited. We generate text samples using an LLM with the Chain-of-Thought (CoT) prompting technique guided by cultural context and examples and then convert them into speech samples using a text-to-speech (TTS) system. However, some of them contain non-hate speech samples with hate-related words, which degrades the censorship performance. This paper filters the samples which text classification models correctly label as hate content. By adjusting the threshold for the number of correct answer models, we can control the level of hate in the generated dataset, allowing us to train the LLMs through curriculum learning in a gradual manner. Experimental results show that the proposed method achieves a masking accuracy of 58.6\% for hate-related words, surpassing previous baselines. We also confirm that the curriculum training contributes to the efficiency of both transcription and censorship tasks.

翻译：本文提出了一种利用大语言模型（LLMs）进行仇恨言论自动语音识别（ASR）的模型。所提出的方法将ASR模型的编码器与LLMs的解码器集成，实现了转录与审查任务的同时执行，以防止有害内容的暴露。对LLM进行指令微调以用特定标记屏蔽仇恨相关词汇，这需要标注的仇恨言论数据集，而此类数据目前较为有限。我们采用链式思维（CoT）提示技术，在文化背景和示例的引导下，利用LLM生成文本样本，然后通过文本转语音（TTS）系统将其转换为语音样本。然而，其中部分样本虽包含仇恨相关词汇却并非仇恨言论，这会降低审查性能。本文通过文本分类模型筛选出被正确标注为仇恨内容的样本。通过调整正确分类模型数量的阈值，我们可以控制生成数据集中仇恨内容的强度，从而能够通过课程学习的方式逐步训练LLMs。实验结果表明，所提出的方法对仇恨相关词汇的屏蔽准确率达到58.6%，超越了现有基线方法。我们还证实了课程训练有助于提升转录和审查任务的综合效率。