Showing 2025Show all
3 papers · 1 filter
cs.SD2025
More Than A Shortcut: A Hyperbolic Approach To Early-Exit Networks
Swapnil Bhosale, Cosmin Frateanu, Camilla Clark +7
Deploying accurate event detection on resource-constrained devices is challenged by the trade-off between performance and computational cost. While Early-Exit (EE) networks offer a…
cs.SD2025
Controlling the Parameterized Multi-channel Wiener Filter using a tiny neural network
Eric Grinstein, Ashutosh Pandey, Cole Li +6
Noise suppression and speech distortion are two important aspects to be balanced when designing multi-channel Speech Enhancement (SE) algorithms. Although neural network models hav…
cs.LG2025
Efficient Neural and Numerical Methods for High-Quality Online Speech Spectrogram Inversion via Gradient Theorem
Andres Fernandez, Juan Azcarreta, Cagdas Bilen +1
Recent work in online speech spectrogram inversion effectively combines Deep Learning with the Gradient Theorem to predict phase derivatives directly from magnitudes. Then, phases…