Picture for Konstantinos Drossos

Konstantinos Drossos

Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning

Add code
Aug 09, 2023
Viaarxiv icon

Adversarial Representation Learning for Robust Privacy Preservation in Audio

Add code
Apr 29, 2023
Viaarxiv icon

Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Network

Add code
Aug 04, 2022
Figure 1 for Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Network
Figure 2 for Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Network
Figure 3 for Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Network
Figure 4 for Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Network
Viaarxiv icon

Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering

Add code
Apr 20, 2022
Figure 1 for Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering
Figure 2 for Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering
Figure 3 for Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering
Figure 4 for Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering
Viaarxiv icon

Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning

Add code
Oct 14, 2021
Figure 1 for Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
Figure 2 for Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
Figure 3 for Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
Figure 4 for Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
Viaarxiv icon

Unsupervised Audio-Caption Aligning Learns Correspondences between Individual Sound Events and Textual Phrases

Add code
Oct 06, 2021
Figure 1 for Unsupervised Audio-Caption Aligning Learns Correspondences between Individual Sound Events and Textual Phrases
Figure 2 for Unsupervised Audio-Caption Aligning Learns Correspondences between Individual Sound Events and Textual Phrases
Figure 3 for Unsupervised Audio-Caption Aligning Learns Correspondences between Individual Sound Events and Textual Phrases
Figure 4 for Unsupervised Audio-Caption Aligning Learns Correspondences between Individual Sound Events and Textual Phrases
Viaarxiv icon

Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations

Add code
Oct 04, 2021
Figure 1 for Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations
Figure 2 for Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations
Figure 3 for Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations
Figure 4 for Fairness and underspecification in acoustic scene classification: The case for disaggregated evaluations
Viaarxiv icon

Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection

Add code
Jul 20, 2021
Figure 1 for Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection
Figure 2 for Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection
Viaarxiv icon

Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach

Add code
Jul 16, 2021
Figure 1 for Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach
Figure 2 for Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach
Figure 3 for Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach
Figure 4 for Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach
Viaarxiv icon

Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit

Add code
Jun 14, 2021
Figure 1 for Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit
Figure 2 for Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit
Figure 3 for Automatic Analysis of the Emotional Content of Speech in Daylong Child-Centered Recordings from a Neonatal Intensive Care Unit
Viaarxiv icon