Dereverberatie en nagalm van audio, muziek en spraak.
The DREAMS Initial Training Network will investigate the problem of modeling, controlling, removing, and synthesizing acoustic reverberation with the aim of enhancing the quality and intelligibility of audio, music, and speech signals. The proposed research and training program builds upon four disciplines that are equally important in understanding and tackling the (de-)reverberation problem: room acoustics, signal processing, psychoacoustics, and speech and audio processing. The strong commitment of the private sector in the proposed ITN consortium, consisting of 4 academic and 8 industrial partners, illustrates the timeliness and importance of the (de-)reverberation problem in a wide variety of applications. However, carrying application-driven solutions is not the only objective of the DREAMS research program. Indeed, the aim is also to take a significant step forward and make fundamental scientific contributions in each of the four disciplines mentioned earlier. To this end, the envisaged ITN will host 12 early stage researchers and 4 experienced researchers, each performing an individual research project around one of four themes that reflect the most challenging open problems in the area of (de-)reverberation. The DREAMS ITN will be implemented such as to maximize the international and intersectoral experience of the research fellows, by defining relevant secondments in academia and industry, both in the host country and abroad. Moreover, experienced researchers will be expected to take on a supervisory role in coordinating one of the four research themes, with the aim of developing solid skills in leadership and research management. Finally, a training program of extremely high quality is proposed, with local as well as network-wide training, which relies on the scientific excellence of the involved partners and of invited external researchers, and which heavily depends on the input of the private sector.