标题： TSPE：用于改进零样本音频分类的任务特定提示集成 显示英文标题

标题： TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification

摘要： 音频语言模型（ALMs）在零样本音频分类任务中表现出色，该任务中模型通过利用描述性的自然语言提示，在测试时对以前未见过的音频片段进行分类。 我们引入了TSPE（任务特定提示集成），一种简单、无需训练的硬提示方法，通过为不同的音频分类任务定制提示来提升ALE的零样本性能。 而不是使用像“汽车的声音”这样的通用模板提示，我们生成上下文丰富的提示，例如“从隧道传来的汽车声音”。 具体而言，我们利用标签信息来识别合适的声学属性，如“响亮”和“微弱”，以及适当的声音来源，如“隧道”和“街道”，并将这些信息纳入音频语言模型（ALMs）用于音频分类的提示中。 此外，为了增强音频文本对齐，我们在TSPE生成的任务特定提示上进行提示集成。 在12个不同的音频分类数据集上评估时，TSPE通过在原始零样本评估基础上显示出1.23-16.36%的绝对改进，从而提升了ALMs的性能。 显示英文摘要

摘要： Audio-language models (ALMs) excel in zero-shot audio classification, a task where models classify previously unseen audio clips at test time by leveraging descriptive natural language prompts. We introduce TSPE (Task-Specific Prompt Ensemble), a simple, training-free hard prompting method that boosts ALEs' zero-shot performance by customizing prompts for diverse audio classification tasks. Rather than using generic template-based prompts like "Sound of a car" we generate context-rich prompts, such as "Sound of a car coming from a tunnel". Specifically, we leverage label information to identify suitable sound attributes, such as "loud" and "feeble", and appropriate sound sources, such as "tunnel" and "street" and incorporate this information into the prompts used by Audio-Language Models (ALMs) for audio classification. Further, to enhance audio-text alignment, we perform prompt ensemble across TSPE-generated task-specific prompts. When evaluated on 12 diverse audio classification datasets, TSPE improves performance across ALMs by showing an absolute improvement of 1.23-16.36% over vanilla zero-shot evaluation.