3 papers
eess.AS2026
PAS-SE: Personalized Auxiliary-Sensor Speech Enhancement for Voice Pickup in Hearables
Mattes Ohlenbusch, Mikolaj Kegler, Marko Stamenovic
Speech enhancement for voice pickup in hearables aims to improve the user's voice by suppressing noise and interfering talkers, while maintaining own-voice quality. For single-chan…
eess.AS2024
CATSE: A Context-Aware Framework for Causal Target Sound Extraction
Shrishail Baligar, Mikolaj Kegler, Bryce Irvin +2
Target Sound Extraction (TSE) focuses on the problem of separating sources of interest, indicated by a user's cue, from the input mixture. Most existing solutions operate in an off…
eess.AS2024
Latent CLAP Loss for Better Foley Sound Synthesis
Tornike Karchkhadze, Hassan Salami Kavaki, Mohammad Rasool Izadi +5
Foley sound generation, the art of creating audio for multimedia, has recently seen notable advancements through text-conditioned latent diffusion models. These systems use multimo…