A neural architecture for computing acoustic-phonetic invariants


The proposed neural architecture consists of an analytic lower net, and a synthetic upper net. This paper focuses on the upper net. The lower net performs a 2D multiresolution wavelet decomposition of an initial spectral representation to yield a multichannel representation of local frequency modulations at multiple scales. From this representation, the… (More)
DOI: 10.1109/ICASSP.1998.675463

4 Figures and Tables


  • Presentations referencing similar topics