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

  • Post category:Publications

Automated audio captioning (AAC) is the task of automatically creating textual descriptions (i.e. captions) for the contents of a general audio signal. Most AAC methods are using existing datasets to optimize and/or evaluate upon.

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

Multi-Exit Vision Transformer for Dynamic Inference

  • Post category:Publications

Underspecification and fairness in machine learning (ML) applications have recently become two prominent issues in the ML community. Acoustic scene classification (ASC) applications have so far remained unaffected by this discussion, but are now becoming increasingly used in real-world systems where fairness and reliability are critical aspects.

Continue Reading Multi-Exit Vision Transformer for Dynamic Inference

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

Underspecification and fairness in machine learning (ML) applications have recently become two prominent issues in the ML community. Acoustic scene classification (ASC) applications have so far remained unaffected by this discussion, but are now becoming increasingly used in real-world systems where fairness and reliability are critical aspects.

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

Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning

  • Post category:Publications

Deploying deep learning services for time-sensitive and resource-constrained settings such as IoT using edge computing systems is a challenging task that requires dynamic adjustment of inference time. Multi-exit architectures allow deep neural networks to terminate their execution early in order to adhere to tight deadlines at the cost of accuracy.

Continue Reading Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning

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

  • Post category:Publications

Researchers have recently started to study how the emotional speech heard by young infants can affect their developmental outcomes. As a part of this research, hundreds of hours of daylong recordings from preterm infants’ audio environments were collected from two hospitals in Finland and Estonia in the context of so-called APPLE study.

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

Enabling energy efficient machine learning on a Ultra-Low-Power vision sensor for IoT

he Internet of Things (IoT) and smart city paradigm includes ubiquitous technology to extract context information in order to return useful services to users and citizens. An essential role in this scenario is often played by computer vision applications, requiring the acquisition of images from specific devices.

Continue Reading Enabling energy efficient machine learning on a Ultra-Low-Power vision sensor for IoT