Audio

MAMKit: A Comprehensive Multimodal Argument Mining Toolkit
MAMKit is an open PyTorch toolkit that puts multimodal argument mining datasets and models behind one interface, so results become easy to reproduce.
Eleonora Mancini, Federico Ruggeri, Stefano Colamonaco, Andrea Zecca, Samuele Marro, Paolo Torroni
Cite Code DOI URL
MAMKit: A Comprehensive Multimodal Argument Mining Toolkit
Multimodal Fallacy Classification in Political Debates
Releases the first corpus pairing political debate text with audio for classifying six fallacy types, and shows that adding audio improves classification for several models.
Cite DOI URL
Multimodal Fallacy Classification in Political Debates
Multimodal Argument Mining: A Case Study in Political Debates
MM-USElecDeb60To16 aligns decades of US presidential debate transcripts with their audio, and shows that pre-trained audio embeddings beat spectral features for argument mining.
Cite URL