Acoustic parameters versus phonetic features in ASR
J.J.M. Koreman, Bistra Andreeva, Helmer Strik · Radboud Repository (Radboud University) · 1999
By mapping acoustic parameters onto phonetic features, it is possible to explicitly address the linguistic information in the signal.For the experiments presented in this paper, we mapped cepstral parameters onto two sets of phonetic features, one based on the IPA chart and the other on SPE.As a result, the phoneme identification rates in a hidden Markov modelling framework increase from 15.6% for the cepstral parameters to 42.3% and 31.7% for the IPA and SPE features, respectively.Furthermore, for phonetic features the resulting confusions between phonemes are often less severe from a phonetic point of view.The theoretical implications of the differences are addressed.