Abstract
This paper presents statistics relating to various phoneme guessing algorithms. The N-phoneme statistics were obtained by exhaustive analysis of a lexicon of 96,998 phonetic words. The results show that by incorporating detailed phonotactic knowledge, coupled with broad phonetic knowledge, an algorithm can be formulated which successfully guesses the correct phoneme with mean success rates of up to 67%. This implies that, as far as the computer is concerned, spoken English is, at a minimum, 67% redundant. The results also show that the ability to guess correctly depends on word length and position; phoneme type and the number of unknown phonemes in the word have very little effect on the final results.
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
