Papers by Yuri Matveev

Copied to clipboard

Challenge:	Existing systems that estimate user preferences only in static manners or exploit interaction history are inadequate to accurately assess user preferences.
Approach:	They propose to integrate rank consistent ordinal regression into a speech-only sentiment prediction task performed by ResNet-like systems and use speaker verification extractors trained on larger datasets as low-level feature extractor.
Outcome:	The proposed system beats state-of-the-art unimodal systems on multimodal Opinion Sentiment and Emotion Intensity databases.