Audio Research Team conducts research and provides education in audio, speech, and music signal processing at Tampere University of Technology, Department of Signal Processing. The research team is part of Multimedia Group. The research of the team focuses mainly on the content analysis of sounds, and its research areas include

The team has produced several state-of-the art results in the areas of audio-based music information retrieval and noise-robust automatic speech recognition.

People

The following people at TUT are involved in INSPIRE projects:

Tuomas Virtanen, Academy Research Fellow
Thomas Barker, PhD student

Most of the other members of the team are post-graduate students conducting research on their doctoral theses, but there are also some post-doctoral researchers and research assistants. The team does active international collaboration by regularly hosting international visitors, and its members regularly visit foreign top universities.

Projects

TUT is the host for one INSPIRE project

ENR-3: Modelling the perceptual grouping of sounds by sparse auditory signal representations. The human auditory system organizes mixtures of sounds into streams using grouping cues such as harmonicity and common modulations. This bottom-up processing contributes to the recognition of sounds in noise. The existing computational models of the phenomenon are very limited. The project will develop a computational model of primary grouping of sounds based on modern machine learning methods such as sparse coding and non-negative matrix factorization, which have been successfully used to stream complex mixtures sounds. The developed model provides a mid-level representation that can be used as a basis of higher-level models to predict speech intelligibility in environmental noises. The representation itself can be used to predict separability of different types of speech and noise.

TUT is also the second host of INSPIRE project ENR-2.