MARVEL and AI Hub Tampere jointly organized the “Audio and Speech Technology Workshop” on 16th June at Paidia workspace in Nokia Arena, Tampere, Finland.

The development of machine learning in combination with signal processing techniques has led to new possibilities in applications that process and analyze audio or speech. The workshop aimed to provide an opportunity to exchange information about the latest development in these fields. There were a number of presentations given by experts studying these topics at Tampere University, as well as selected case studies provided by 3 companies and 2 projects, including MARVEL.

The morning session focused on giving an overview of different applications that can be addressed by audio and speech technologies, followed by discussing data and machine learning techniques that are needed or can be used in the development of the methods. The afternoon session included case study presentations from companies and selected projects, as well as a hands-on tutorial that explains how to build sound classifiers, use pre-trained audio models for audio tagging, and how to implement speech processing with existing toolboxes.

The workshop was organized in a hybrid format with approximately 50 attendees joining either physically or remotely. For more information on the workshop, you can also visit the AI Hub Tampere relative page here