Session 2.3: Speech & Sound Processing

Monday Afternoon, May 29

Session 2.3:	Speech & Sound Processing
Time & Place:	14:00 - 16:00, Daphine
Chairperson:	A. M. Krot Institute of Engineering Cybernetics, National Academy of Science of Belarus, Belarus

2.3.1	14:00 Score extraction using MPEG-4 T/F partial encoding I. Barrera, F. Tarres Teoria de la Senyal y Communicaciones Department, Escola Universitaria Politecnica del Baix Llobregat, Universitat Politecnica de Catalunya, Spain
2.3.2	14:15 Transcription of polyphonic piano music with neural networks M. Marolt Faculty of Computer and Information Science, University of Ljubljana, Slovenia
2.3.3	14:30 Interactive dialogue telephone service Lj. Stanimirovic Telecommunications Department, Mihajlo Pupin Institute, Yugoslavia
2.3.4	14:45 Speech signal recovery in packet-switched communication networks V. Zagursky, E. Ginters Institute of Electronics and Computer Science of Latvian University, Latvia
2.3.5	15:00 On approach to speech recognition using non-linear signal decomposition into Volterra-Wiener functional series A. M. Krot¹, P. P. Tkachova² ¹Institute of Engineering Cybernetics, National Academy of Science of Belarus, Belarus ²Belarusian State University, Belarus
2.3.6	15:15 Short-term sound stream characterization for reliable, real-time occurrence monitoring of given sound-prints G. Richly, L. Varga, F. Kovacs, G. Hosszu Department of Electron Devices, Technical University of Budapest, Hungary