no code implementations • 21 Mar 2024 • Shrishail Baligar, Mikolaj Kegler, Bryce Irvin, Marko Stamenovic, Shawn Newsam
First, we explore the utility of context by providing the TSE model with oracle information about what sound classes make up the input mixture, where the objective of the model is to extract one or more sources of interest indicated by the user.
1 code implementation • 18 Mar 2024 • Tornike Karchkhadze, Hassan Salami Kavaki, Mohammad Rasool Izadi, Bryce Irvin, Mikolaj Kegler, Ari Hertz, Shuo Zhang, Marko Stamenovic
We introduce a new loss term to enhance Foley sound generation in AudioLDM without post-filtering.
no code implementations • 15 Sep 2023 • Rayan Daod Nathoo, Mikolaj Kegler, Marko Stamenovic
Tiny, causal models are crucial for embedded audio machine learning applications.
no code implementations • 4 Nov 2022 • Yuchen Liu, Li-Chia Yang, Alex Pawlicki, Marko Stamenovic
Speech quality assessment has been a critical component in many voice communication related applications such as telephony and online conferencing.
1 code implementation • 4 Nov 2022 • Bryce Irvin, Marko Stamenovic, Mikolaj Kegler, Li-Chia Yang
Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction.
no code implementations • 3 Nov 2021 • Marko Stamenovic, Nils L. Westhausen, Li-Chia Yang, Carl Jensen, Alex Pawlicki
Using weight pruning, we show that we are able to compress an already compact model's memory footprint by a factor of 42x from 3. 7MB to 87kB while only losing 0. 1 dB SDR in performance.
1 code implementation • 20 May 2020 • Igor Fedorov, Marko Stamenovic, Carl Jensen, Li-Chia Yang, Ari Mandell, Yiming Gan, Matthew Mattina, Paul N. Whatmough
Modern speech enhancement algorithms achieve remarkable noise suppression by means of large recurrent neural networks (RNNs).
1 code implementation • 20 May 2020 • Marko Stamenovic
A cover song, by definition, is a new performance or recording of a previously recorded, commercially released song.
no code implementations • 20 May 2020 • Marko Stamenovic, Jeibo Luo
This new dataset allows us to expand on current work in the field by generalizing across time and academic domain.