SpMis: An Investigation of Synthetic Spoken Misinformation Detection

TL;DR

This paper introduces SpMis, a new dataset for detecting synthetic spoken misinformation, highlighting the challenges and potential of current detection methods amidst advancing speech synthesis technology.

Contribution

The paper presents SpMis, an open-source dataset for synthetic spoken misinformation detection, and provides initial analysis demonstrating detection challenges and opportunities.

Findings

Promising detection results with current methods

Significant challenges remain for practical misinformation detection

Dataset includes speech from over 1,000 speakers on five topics

Abstract

In recent years, speech generation technology has advanced rapidly, fueled by generative models and large-scale training techniques. While these developments have enabled the production of high-quality synthetic speech, they have also raised concerns about the misuse of this technology, particularly for generating synthetic misinformation. Current research primarily focuses on distinguishing machine-generated speech from human-produced speech, but the more urgent challenge is detecting misinformation within spoken content. This task requires a thorough analysis of factors such as speaker identity, topic, and synthesis. To address this need, we conduct an initial investigation into synthetic spoken misinformation detection by introducing an open-source dataset, SpMis. SpMis includes speech synthesized from over 1,000 speakers across five common topics, utilizing state-of-the-art text-to-speech systems. Although our results show promising detection capabilities, they also reveal substantial challenges for practical implementation, underscoring the importance of ongoing research in this critical area.