Search Results - "Irvin, Bryce"

  • Showing 1 - 7 results of 7
Refine Results
  1. 1

    Self-Supervised Learning for Speech Enhancement Through Synthesis by Irvin, Bryce, Stamenovic, Marko, Kegler, Mikolaj, Yang, Li-Chia

    “…Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative…”
    Get full text
    Conference Proceeding
  2. 2

    CATSE: A Context-Aware Framework for Causal Target Sound Extraction by Baligar, Shrishail, Kegler, Mikolaj, Irvin, Bryce, Stamenovic, Marko, Newsam, Shawn

    “…Target Sound Extraction (TSE) focuses on the prob-lem of separating sources of interest, indicated by a user's cue, from the input mixture. Most existing…”
    Get full text
    Conference Proceeding
  3. 3

    A Fullband Neural Network for Audio Packet Loss Concealment by Irvin, Bryce, Yin, Sile, Zhang, Shuo, Stamenovic, Marko

    “…Audio packet loss, a result of missing or irregular packets, significantly degrades speech quality in voice communications. The ICASSP 2024 Audio Deep Packet…”
    Get full text
    Conference Proceeding
  4. 4

    CATSE: A Context-Aware Framework for Causal Target Sound Extraction by Baligar, Shrishail, Kegler, Mikolaj, Irvin, Bryce, Stamenovic, Marko, Newsam, Shawn

    Published 21-03-2024
    “…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…”
    Get full text
    Journal Article
  5. 5

    Self-Supervised Learning for Speech Enhancement through Synthesis by Irvin, Bryce, Stamenovic, Marko, Kegler, Mikolaj, Yang, Li-Chia

    Published 04-11-2022
    “…Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative…”
    Get full text
    Journal Article
  6. 6

    Latent CLAP Loss for Better Foley Sound Synthesis by Karchkhadze, Tornike, Kavaki, Hassan Salami, Izadi, Mohammad Rasool, Irvin, Bryce, Kegler, Mikolaj, Hertz, Ari, Zhang, Shuo, Stamenovic, Marko

    “…Foley sound generation, the art of creating audio for multimedia, has recently seen notable advancements through text-conditioned latent diffusion models…”
    Get full text
    Conference Proceeding
  7. 7

    Latent CLAP Loss for Better Foley Sound Synthesis by Karchkhadze, Tornike, Kavaki, Hassan Salami, Izadi, Mohammad Rasool, Irvin, Bryce, Kegler, Mikolaj, Hertz, Ari, Zhang, Shuo, Stamenovic, Marko

    Published 18-03-2024
    “…EUSIPCO 2024 Proceedings, ISBN: 978-9-4645-9361-7 Foley sound generation, the art of creating audio for multimedia, has recently seen notable advancements…”
    Get full text
    Journal Article