ProSarc: Prosody-Aware Sarcasm Recognition Framework via Temporal Prosodic Incongruity
Researchers have developed ProSarc, a novel framework for detecting sarcasm in audio by analyzing temporal prosodic incongruity. This method identifies mismatches between local speech patterns and the overall emotional tone of an utterance. ProSarc demonstrates superior performance on multiple datasets, outperforming previous audio-only approaches and showing generalizability across different speech types. AI
IMPACT This framework could improve the accuracy of sentiment analysis and content moderation systems by better understanding nuanced human communication.