Acoustic phonetic data base for the study of selected English consonants, consonant clusters, and vowels

Abstract

Improved understanding of the acoustics of speech events and recent advances in speech analysis techniques, combined with the availability of large and fast computers, have enabled speech researchers to examine and interpret a large corpus of acoustic data. These reasons provided motivation for constructing an acoustic phonetic data base where the acoustic characteristics of speech sounds can be studied in a detailed and systematic way. The data base includes a substantial number of nonsense CVC utterances (embedded in a carrier sentence) produced by several speakers. The consonants and the vowel are systematically varied. Using the acoustic analysis system that has been implemented, analog recordings can be digitized and processed (via DFT or linear prediction) in real time. The waveform, spectra, and hand-marked phonetic labels are stored on digital tapes for later referencing. During the presentation of this paper, the display and data analysis capabilities of the data-base will be demonstrated. Results on the relative durations of frication and aspiration of voiceless plosives, and results on rapid spectral changes at the release of stops will be presented.