9 papers
From Triage to Impact: A Multi-Hop Reasoning Benchmark for Explainable Persian Hate Speech
Ghazal Kalhor, Sima Kamandloo, Mehrsa Shamsian +1
Hate speech has become increasingly prevalent on social media, raising concerns about its detection, interpretation, and moderation. Persian, a relatively low-resource language, la…
Physics-Guided Variational Model for Unsupervised Sound Source Tracking
Luan Vinícius Fiorio, Ivana Nikoloska, Bruno Defraene +3
Sound source tracking is commonly performed using classical array-processing algorithms, while machine-learning approaches typically rely on precise source position labels that are…
Clustering of Acoustic Environments with Variational Autoencoders for Hearing Devices
Luan Vinícius Fiorio, Ivana Nikoloska, Wim van Houtum +1
Traditional acoustic environment classification relies on: i) classical signal processing algorithms, which are unable to extract meaningful representations of high-dimensional dat…
Hybrid Real- and Complex-Valued Neural Network Architecture for Speech Enhancement
Luan Vinícius Fiorio, Alex Young, Ronald M. Aarts
This paper investigates hybrid real- and complex-valued neural networks for monaural speech enhancement. While complex-valued models can process time-frequency representations nati…
Hybrid Real- and Complex-valued Neural Network Architecture
Alex Young, Luan Vinícius Fiorio, Bo Yang +3
We propose a \emph{hybrid} real- and complex-valued \emph{neural network} (HNN) architecture, designed to combine the computational efficiency of real-valued processing with the ab…
Categorical Unsupervised Variational Acoustic Clustering
Luan Vinícius Fiorio, Ivana Nikoloska, Ronald M. Aarts
We propose a categorical approach for unsupervised variational acoustic clustering of audio data in the time-frequency domain. The consideration of a categorical distribution enfor…
Target Speaker Selection for Neural Network Beamforming in Multi-Speaker Scenarios
Luan Vinícius Fiorio, Bruno Defraene, Johan David +4
We propose a speaker selection mechanism (SSM) for the training of an end-to-end beamforming neural network, based on recent findings that a listener usually looks to the target sp…
Unsupervised Variational Acoustic Clustering
Luan Vinícius Fiorio, Bruno Defraene, Johan David +3
We propose an unsupervised variational acoustic clustering model for clustering audio data in the time-frequency domain. The model leverages variational inference, extended to an a…
Spectral Masking with Explicit Time-Context Windowing for Neural Network-Based Monaural Speech Enhancement
Luan Vinícius Fiorio, Boris Karanov, Bruno Defraene +4
We propose and analyze the use of an explicit time-context window for neural network-based spectral masking speech enhancement to leverage signal context dependencies between neigh…