Perceptual Audio, Masking Models, Hearing Science, Lossy Compression
Ripping CDs the old way
thefoggiest.devΒ·19h
ReMAR-DS: Recalibrated Feature Learning for Metal Artifact Reduction and CT Domain Transformation
arxiv.orgΒ·1d
Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices
arxiv.orgΒ·2d
SLAP: Siamese Language-Audio Pretraining Without Negative Samples for Music Understanding
arxiv.orgΒ·2d
Rethinking Mean Opinion Scores in Speech Quality Assessment: Aggregation through Quantized Distribution Fitting
arxiv.orgΒ·2d
Face-Voice Association for Audiovisual Active Speaker Detection in Egocentric Recordings
arxiv.orgΒ·2d
Loading...Loading more...