Stars
The first comprehensive multimodal language analysis benchmark for evaluating foundation models
MMSA is a unified framework for Multimodal Sentiment Analysis.
Multimodal Feature Extraction Pipeline: A comprehensive tool for processing video files to perform speaker diarization and extract a rich set of features encompassing acoustic, linguistic, and faci…
audio-extract is a Python library that allows you to extract audio from video files and trim the audio according to your needs.
Tool to analyze an audio corpora in terms of intonation, intensity, duration and voice quality
The first opensource platform for multimodal intent analysis
Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances (ACL 2024)
AdaFN-AG: Enhancing Multimodal Interaction with Adaptive Feature Normalization for Multimodal Sentiment Analysis