Abstract
Stokes (1996) demonstrated that visual inspection of raw complex waveforms can be used to identify a vowel produced by a talker. This research resulted in the MAS Model of Vowel Perception and Production (Stokes, 1998; http://home.indy.net/∼masmodel/). More recently, another experiment extended this work to female talkers as well as male talkers (Stokes, 2001). Together, this research represents the only ongoing comprehensive research involving visual inspection of raw complex waveforms for identifying vowels produced by any talker. As an extension of the work, the present study involves identifying a talker from a waveform display. Unique voice signatures identified from waveform displays are used to identify a talker from a set of 10 talkers in the same way as one would identify a person from fingerprints. In two trials (the word who’d in trial 1 and heed in trial 2), a talker was correctly identified from a set of 10 unique talkers per trial using small visual samples of waveforms and matching it to a waveform sample of the talkers to be identified.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
