CCATMos: Convolutional Context-aware Transformer Network for Non-intrusive Speech Quality Assessment

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.

Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators

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.

Model Compression Speech Enhancement