Phoneme Recognition: Neural Networks vs. Hidden Markov Models
Alex Waibel, Toshiyuki Hanazawa, Geoffrey E. Hinton, Kiyohiro Shikano, Lang, K. · 1988
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-propagatioii[l]. 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