This research focuses on understanding the information encoded in speech processing by using vector representations of speech from a pretrained model. The study proposes an unsupervised method using ABX tests…
Continue readingThis research article discusses a matrix factorization technique that decomposes signals into components, each of which is regularized to ensure it nearly satisfies the constraints imposed by the wave equation….
Continue readingThe paper explores the potential of diffusion models in unsupervised learning. Such models use a U-Net to predict and remove noise, resulting in the synthesis of high-quality, diverse images. The…
Continue readingThis study introduces SpectralMix, a joint dimensionality reduction technique for multi-relational graphs with categorical node attributes. SpectralMix integrates all information available from the attributes, the different types of relations, and…
Continue readingThe research article presents a new framework for unsupervised video anomaly detection (VAD) called Coarse-to-Fine Pseudo-Labeling (C2FPL). Traditional VAD methods rely heavily on manually annotated anomaly examples, which is a…
Continue readingThe paper discusses a novel framework for first-shot unsupervised anomalous sound detection (ASD). It is a task introduced in DCASE 2023 Challenge Task 2. The traditional ASD methods, which rely…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
