INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS Int. J. Circ. Theor. Appl. 2006; 34:489–515 Published online in Wiley InterScience (www.interscience.wiley.com). DOI: 10.1002/cta.362 Computational auditory scene analysis in cellular wave computing framework Zolt´ an Fodr´ oczi 1, ∗, † and Andr´ as Radv´ anyi 2, ‡ 1 Faculty of Information Technology, P´ azm´ any University, Pr´ ater u. 50/A, Budapest H-1058, Hungary 2 Analogic and Neural Computing Laboratory, Computer and Automation Research Institute, Hungarian Academy of Sciences, Kende u. 13-17, Budapest H-1111, Hungary SUMMARY Extracting substantive auditory objects from an auditory mixture is a widely studied and difficult problem in auditory research. Computational auditory scene analysis (CASA) aims at extracting objects in the frequency domain, based on a set of psychoacoustic grouping procedures. To mimic some aspects of the human auditory system a new cellular neural/non-linear network (CNN)-based library of procedures forming an Auditory Wave Computing Toolkit (AWCT) is presented here. Copyright 2006 John Wiley & Sons, Ltd. Received 10 June 2005; Revised 16 March 2006 KEY WORDS: computational auditory scene analysis; cellular neural networks (CNN); CNN Universal Machine (CNN-UM); wave computer; auditory pre-processing; wave computation; sound source localization 1. INTRODUCTION In the workspace of the future, ‘ambient intelligence’ will be realized through the widespread use of sensors (e.g. cameras, microphones) connected to computers that are unobtrusive to their human users. Towards the end of ambient computing, technological advances in sound analysis are needed in order to solve several basic problems, such as speaker localization and tracking, speech activity detection or automatic speech recognition of distant talk. The long-term goal is the ability to monitor speakers and noise sources in a real reverberant environment, with acceptable constraint on the distribution of microphones or on the number of active sound sources. ∗ Correspondence to: Zolt´ an Fodr´ oczi, Faculty of Information Technology, P´ azm´ any University, Pr´ ater u. 50/A, Budapest H-1058, Hungary. † E-mail: fodroczi@itk.ppke.hu ‡ E-mail: radvanyi@sztaki.hu Contract/grant sponsor: Hungarian National Research Fund; contract/grant number: OTKA-TS40858 Copyright 2006 John Wiley & Sons, Ltd.