14th International Congress of Phonetic Sciences (ICPhS-14) San Francisco, CA, USA August 1-7, 1999

Acoustic Parameters versus Phonetic Features in ASR

Jacques Koreman (1), Bistra Andreeva (1), Helmer Strik (2)

(1) Institute of Phonetics, University of the Saarland, Saarbrücken, Germany
(2) A2RT, Dept. of Language and Speech, University of Nijmegen, Nijmegen, The Netherlands

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.

Full Paper

Bibliographic reference.  Koreman, Jacques / Andreeva, Bistra / Strik, Helmer (1999): "Acoustic parameters versus phonetic features in ASR", In ICPhS-14, 719-722.