Title :
Whole-word phonetic distances and the PGPfone alphabet
Author_Institution :
Dept. of Exp. Psychol., Oxford Univ.
Abstract :
Like many cryptosystems, PGPfone requires a method of reliably exchanging binary data over noisy phone lines. This paper describes a method of encoding binary data into a “radio alphabet” using a feature-based distance metric to measure phonetic confusibility, then using this metric in a genetic algorithm to select appropriate words from a larger list of candidate words. This work indicates several larger issues that should be addressed in any (human) language engineering project
Keywords :
cryptography; encoding; natural languages; speech coding; speech processing; PGPfone alphabet; binary data encoding; cryptosystems; feature-based distance metric; genetic algorithm; language engineering project; noisy phone lines; phonetic confusibility; whole-word phonetic distances; Colored noise; Cryptography; Databases; Encoding; Frequency measurement; Human factors; Psychology; Reliability engineering; Software engineering; Speech;
Conference_Titel :
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location :
Philadelphia, PA
Print_ISBN :
0-7803-3555-4
DOI :
10.1109/ICSLP.1996.607046
