Unsupervised neural networks for speech perception with Cochlear Implant systems for the profoundly deaf
Recently we have proposed a new speech processing concept for Cochlear Implant (CI) — systems. The concept is based on speaker independent signal representation and a neural net classifier which can be combined with the well known CI- speech-coding-strategies. This paper describes some new simulation results: For every speech input frame a 4- dimensional feature vector has been extracted by employing a relative spectral perceptual linear predictive (RASTA-PLP) technique. To classify the feature vectors into so called “auditory related units (ARU)” we applied the self-organizing Kohonen neural net The best matching ARU's will directly control the synthesis of a “alphabet” of patient adapted stimulus patterns. Simulation results show that the Kohonen algorithm finds representative clusters in the feature vector space for different net dimensions. A discussion of the results and a overview of present experiments with deaf patients will be given.
Unable to display preview. Download preview PDF.
- Leisenberg, M., A concept of an adaptive, neural net based cochlear-implant-system using speaker independent signal representation, Proc. International Symposium on cochlear implants, Toulouse, Fr.1992Google Scholar
- Hermansky, H., Perceptual linear predictive analysis of speech, J.Acoust. Soc. Am 1990; 87Google Scholar
- Morgan, N., Compensation for the effect of the communication channel in auditory-like analysis of speech, Proc. Eurospeech'91, Genova, 1991Google Scholar
- Windheuser, C., Competitive Sequence Learning, Diplomarbeit Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn 1991Google Scholar
- Parten CR (ed), Handbook of neural computing applications. San Diego: Academic Press, 1990Google Scholar
- Kohonen, T.: The self-organizing map, Proc. IEEE, 78 (1990) 9, p, 1464 ff.Google Scholar
- Kohonen, T., Kangas, J., Laaksonen, J., SOM-PAK-The Self-Organizing Map Program Package, TR, Helsinki University of Technology, Helsinki 1992Google Scholar
- Leisenberg, M., Downes, M.: CINSTIM: The Southampton Cochlear Implant/Neural network STTMulation framework-implementation advances of a new, neural net based speech processing concept, International Cochlear Implant, Speech and Hearing Symp., October 1994, Melbourne, AustraliaGoogle Scholar