Finished projects

1 September, 2013 - 31 August, 2016

ASISTO

Automatic Speech analysis during Speech Therapy in Oncology

Every year there are more than 4000 new cases in Belgium and the Netherlands of cancer in the head and neck area. Thanks to new treatments the chance of surviving has strongly increased. However, these patients often experience difficulties during eating, drinking and communicating. The communication problems can partly be alleviated by adapted speech therapy which is supported by regular evaluations of the attained speech quality. Recent  research in our group has demonstrated that digital speech processing can offer a cheap and reliable solution here.

1 January, 2004 - 31 December, 2015

COST278BN

Audio indexing of Broadcast News files in different languages

Introduction

In the context of the the European COST action on Spoken Language Interaction in Telecommunication, an international collaboration in the domain of Broadcast News Transcription was started up in 2004. The focus of the collaboration was on audio indexing, but there were some activities on speech transcription as well. The creation of the COST278BN database is considered as one of the big achievements of the&nbsp

1 January, 2011 - 31 December, 2014

TAD

Technical Terminology and Aids for Dyslexia

The DSSP group collaborates with UZ - Gent to produce technical term lists with pronunciation and word frequency information. The users of computer software for dyslectic people, such as Sprint (from Jabbla), will soon be able to download these dictionaries in the software packages.

1 January, 2010 - 31 December, 2013

RECAP

Reservoir Computing for Auditive Pattern Recognition

The aim of this project is to carry out fundamental research into the application of reservoir computing (RC) for some challenging auditory pattern recognition applications such as spatial environment recognition from a multi-channel sonar signal, continuous speech recognition in background noise and instrument recognition in polyphonic music. These applications have in common that they use similar time-frequency representations of the signals and that they require an explicit dynamic behaviour of the pattern recognition system.

1 January, 2010 - 31 December, 2012

CLARIN - TTNWW

Language and Speech Technology Tools for Dutch as web services in a workflow

This project is contributing to the pan-European initiative CLARIN that is aiming at the creation of language and speech technology tools as web services and to advertise these services to human science researchers.

1 August, 2010 - 31 July, 2012

SAPIM

Smart audio processing for interactive multimedia

The aim of this project whic runs in close collaboration with SampleSumo, is to develop novel music signal processing methods that can be embedded in innovative solutions for music production and game development. One of our aims is to extract sound properties and to recognize predefined sounds so as to facilitate the introduction of sounds as an active component in games. Furthermore we will automatically extract musical content with the aim of creating new types of music  visualization (e.g. in  VJ software).

1 April, 2009 - 1 April, 2012

ORGANIC

Self-organized recurrent neural learning for language processing

This EU-FP7 project aims at investigating whether it is possible to incorporate principles of human brain processing (such as self-organization, deep hierarchical processes, fast adaptation, supervised and unsupervised learning) into a new type of automatic speech recognizer. We will attempt to reach our goal by adopting the paradigm of reservoir computing because it has been demonstrated recently that this paradigm allows one to build accurate and robust (against noise) isolated digit recognizers.

1 January, 2004 - 31 December, 2010

SEMA

Semantic description of audio with applications in audio-mining, interactive multimedia and brain research

This project builds on the results of the MAMI project, but it tries to extend the content analysis to the level of semantic descriptions of music. Such descriptions are closer to the way humans express how they perceive the music in terms of affections (sad, happy, romantic, etc.)

1 January, 2007 - 31 December, 2010

TELEX

Combining acoustic TEmplates and LEXical modeling

This FWO-funded project aims at combining bottom-up phonetic recognition and long span example based recognition into a single speech recognition architecture that beats mainstream state-of-the-art HMM systems in terms of accuracy, be it at a higher computational cost. The project runs in collaboration with KULeuven.

1 February, 2008 - 30 September, 2010

AUTONOMATA Too

Automata for deriving phoneme transcriptions of Dutch and Flemish names, Transfer of output

This STEVIN project is about the investigation of new pronunciation modeling technologies that can improve the automatic recognition of spoken names in the context of a POI (Point-of-Interest) information providing business service. Collaboration with RU (Nijmegen), UiL (Utrecht), Nuance and TeleAtlas.