AudioTrust Audio Benchmark Dataset

This dataset is a large-scale audio-text benchmark dataset. As the first multi-dimensional trust evaluation benchmark tailored for large audio models, AudioTrust focuses on evaluating the multi-dimensional credibility of audio large language models (ALLMs). The relevant paper results are:AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models".

Dataset overview:

• Contains 4,420+ real-scene audio-text data, covering 18 real-world scenarios such as daily conversations, emergency calls, and voice assistants.

• Task type: audio anti-spoofing detection, voice command recognition, content authenticity verification, multimodal semantic alignment.

• Modality: Audio (voice instructions, deceptive audio), Text (instruction description, evaluation label).