Key points are not available for this paper at this time.
neme recognition which is characterized by two important properties: 1.) Using a 3 layer arrangement of simple computing units, it can rep-resent arbitrary nonlinear decision surfaces. The TDNN learns these decision surfaces automatically using error back-propagatioiil. 2.) he time-delay arrangement enables the network to discover acoustic-honetic features and the temporal relationships between them inde-endent of position in time and hence not blurred by temporal shifts in the input. For comparison, several discrete Hidden Markov Mod-els (HMM) were trained to perform the same task, i.e., the speaker-dependent recognition of the phonemes B, D, and G extracted We show that the TDNN invented well-known acoustic-phonetic to the same concept. 1
Waibel et al. (Fri,) studied this question.