Shabnam Ghaffarzadegan
YOU?
Author Swipe
View article: DCASE 2024 Challenge Task 10 Evaluation Dataset: Acoustic-based Traffic Monitoring
DCASE 2024 Challenge Task 10 Evaluation Dataset: Acoustic-based Traffic Monitoring Open
Directory structure: locX.zip|----- test [test flac files inside] NOTE: We split zip files for large size folders (i.e., loc1, loc3, loc6). Please make sure to download all splits before unzipping the data! For example, run zip -s 0 loc6.z…
View article: Two vs. Four-Channel Sound Event Localization and Detection
Two vs. Four-Channel Sound Event Localization and Detection Open
Sound event localization and detection (SELD) systems estimate both the direction-of-arrival (DOA) and class of sound sources over time. In the DCASE 2022 SELD Challenge (Task 3), models are designed to operate in a 4-channel setting. Whil…
View article: Unsupervised Discriminative Learning of Sounds for Audio Event Classification
Unsupervised Discriminative Learning of Sounds for Audio Event Classification Open
Recent progress in network-based audio event classification has shown the\nbenefit of pre-training models on visual data such as ImageNet. While this\nprocess allows knowledge transfer across different domains, training a model on\nlarge-s…
View article: Visualizing Classification Structure of Large-Scale Classifiers
Visualizing Classification Structure of Large-Scale Classifiers Open
We propose a measure to compute class similarity in large-scale classification based on prediction scores. Such measure has not been formally pro-posed in the literature. We show how visualizing the class similarity matrix can reveal hiera…
View article: Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable Filterbanks
Towards Domain Invariant Heart Sound Abnormality Detection Using Learnable Filterbanks Open
The proposed methods pave the way for deploying automated cardiac screening systems in diversified and underserved communities.
View article: An Ontology-Aware Framework for Audio Event Classification
An Ontology-Aware Framework for Audio Event Classification Open
Recent advancements in audio event classification often ignore the structure and relation between the label classes available as prior information. This structure can be defined by ontology and augmented in the classifier as a form of doma…
View article: Self-supervised Attention Model for Weakly Labeled Audio Event Classification
Self-supervised Attention Model for Weakly Labeled Audio Event Classification Open
We describe a novel weakly labeled Audio Event Classification approach based on a self-supervised attention model. The weakly labeled framework is used to eliminate the need for expensive data labeling procedure and self-supervised attenti…
View article: An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification
An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification Open
In this work, we propose an ensemble of classifiers to distinguish between various degrees of abnormalities of the heart using Phonocardiogram (PCG) signals acquired using digital stethoscopes in a clinical setting, for the INTERSPEECH 201…
View article: Deep Multiple Instance Feature Learning via Variational Autoencoder
Deep Multiple Instance Feature Learning via Variational Autoencoder Open
We describe a novel weakly supervised deep learning framework that combines both the discriminative and generative models to learn meaningful representation in the multiple instance learning (MIL) setting. MIL is a weakly supervised learni…
View article: Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection
Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection Open
Automatic heart sound abnormality detection can play a vital role in the early diagnosis of heart diseases, particularly in low-resource settings. The state-of-the-art algorithms for this task utilize a set of Finite Impulse Response (FIR)…
View article: Deep neural network training for whispered speech recognition using small databases and generative model sampling
Deep neural network training for whispered speech recognition using small databases and generative model sampling Open
State-of-the-art speech recognition solutions currently employ hidden Markov models (HMMs) to capture the time variability in a speech signal and deep neural networks (DNNs) to model the HMM state distributions. It has been shown that DNN–…