SpMis: An Investigation of Synthetic Spoken Misinformation Detection
This addresses the urgent challenge of detecting misinformation in synthetic speech, which is critical for mitigating misuse of speech generation technology, but it is an incremental step as it focuses on dataset creation and initial investigation.
The paper tackles the problem of detecting synthetic misinformation in spoken content by introducing an open-source dataset, SpMis, which includes speech from over 1,000 speakers across five topics using state-of-the-art text-to-speech systems, showing promising detection capabilities but highlighting substantial challenges for practical implementation.
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.