Skip to content

VoiceVision: AI-Powered Speaker-Aware Cropping and Content Indexing for Multi-Speaker Videos.

Mehdi Houshmand Sarkhoosh, Cise Midoglu, Saeed Shafiee Sabet, Tomas Kupka, Pl Halvorsen

VenueCCBMI
Year2025
ProceedingsCBMI

Browse the full CBMI paper archive.