• Publications
  • Influence
Scent dog identification of samples from COVID-19 patients – a pilot study
TLDR
Preliminary findings indicate that trained detection dogs can identify respiratory secretion samples from hospitalised and clinically diseased SARS-CoV-2 infected individuals by discriminating between samples from SATS infected patients and negative controls.
Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery
TLDR
A VAE with Hidden Markov Models (HMMs) as latent models was developed and applied to the task of acoustic unit discovery in a zero resource scenario, demonstrating for an unsupervised learning task what is well-known in the supervised learning case: Neural networks provide superior modeling power compared to GMMs.
Convolutional Recurrent Neural Network and Data Augmentation for Audio Tagging with Noisy Labels and Minimal Supervision
TLDR
This paper proposes a model consisting of a convolutional front end using log-mel-energies as input features, a recurrent neural network sequence encoder and a fully connected classifier network outputting an activity probability for each of the 80 considered event classes.
Forward-Backward Convolutional Recurrent Neural Networks and Tag-Conditioned Convolutional Neural Networks for Weakly Labeled Semi-supervised Sound Event Detection
TLDR
The presented system for the detection and classi-fication of acoustic scenes and events (DCASE) 2020 Challenge and a tag-conditioned CNN tocomplement SED is proposed, trained to predict strong labels while using weak labels, as additional input.
Full Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery
TLDR
The Bayesian Hidden Markov Model Variational Autoencoder (BHMMVAE) is introduced which is able to autonomously infer a reasonable number of acoustic units, can be initialized without supervision by a GMM-HMM system, achieves computationally efficient stochastic variational inference by using natural gradient descent, and improves the AUD performance over the HMMvaE.
Scent dog identification of SARS-CoV-2 infections in different body fluids
TLDR
The scent cognitive transfer performance between inactivated and non-inactivated samples as well as between different sample materials indicates that global, specific SARS-CoV-2-associated volatile compounds are released across different body secretions, independently from the patient’s symptoms.
SOUND EVENT DETECTION USING METRIC LEARNING AND FOCAL LOSS FOR DCASE
TLDR
The main module in the MLFL system is named MLFL, which uses metric learning and focal loss, adopts the weakly-supervised learning framework with an attention-based embedding-level pooling module and the mean-teacher method for semi- supervised learning.
Unsupervised Learning of a Disentangled Speech Representation for Voice Conversion
TLDR
This contribution proposes to employ convolutional instead of recurrent network layers in the encoder and decoder blocks, which is shown toachieve better phone recognition accuracy on the latent segmentvariables at frame-level due to their better temporal resolution.
Contrastive Predictive Coding Supported Factorized Variational Autoencoder For Unsupervised Learning Of Disentangled Speech Representations
TLDR
It is shown that the proposed technique is capable of separating speaker and content traits into the two different representations and show competitive speaker-content disentanglement performance compared to other unsupervised approaches.
Privacy-Preserving Variational Information Feature Extraction for Domestic Activity Monitoring versus Speaker Identification
TLDR
It is empirically demonstrated that the proposed method reduces speaker identification privacy risks without significantly deprecating the performance of domestic activity monitoring tasks.
...
...