ICASSP 2023

Multitaper-Mel Spectrograms for Keyword Spotting

Sampling-Frequency-Independent Convolutional Layer and its Application to Audio Source Separation

USEV: Universal Speaker Extraction With Visual Cue

Selective Listening by Synchronizing Speech With Lips

Non-Bayesian Parametric Missing-Mass Estimation

Use of Speaker Recognition Approaches for Learning and Evaluating Embedding Representations of Musical Instrument Sounds

Graph Signal Processing: Dualizing GSP Sampling in the Vertex and Spectral Domains

BYOL for Audio: Exploring Pre-Trained General-Purpose Audio Representations

Signal Useful Information Recovery by Overlapping Supports of Time-Frequency Representations

MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training

Robust Aggregation for Federated Learning

Decorrelating Feature Spaces for Learning General-Purpose Audio Representations