Universal Publishers has put out the Waveform Model of Vowel Perception and Production. 

In addition to describing waveform displays of vowels beyond previous descriptions, included in the book are descriptions of experimental evidence supporting near-100 percent vowel identification accuracy across 20 male talkers using the concepts in the model. The ability to identify female vowel productions has also been demonstrated. This work with waveforms more than compliments work achieved from spectrogram analysis.

The Waveform Model could possibly be used to improve accuracy and speed within existing speech recognition systems, or generate new speech recognition applications. The Waveform Model requires no training, can be used across talkers, and has accuracy above reported speech recognition performance (specific to vowels). The association of the lips and tongue to the production of a vowel also has the possibility of speech production applications. 

The background of the author and links to Amazon and other retailers can be found at http://home.indy.net/~masmodel/. The Waveform Model has the possibility of contributing to both academic research and speech technology products.