Open AccessModeling words with subword units in an articulatorily constrained speech recognition algorithm
Author(s) -
John Hogden
Publication year - 1997
Language(s) - English
Resource type - Reports
DOI - 10.2172/645489
Subject(s) - speech recognition , string (physics) , computer science , word (group theory) , sequence (biology) , hidden markov model , acoustic model , word recognition , natural language processing , artificial intelligence , speech processing , mathematics , linguistics , philosophy , geometry , reading (process) , biology , mathematical physics , genetics
The goal of speech recognition is to find the most probable word given the acoustic evidence, i.e. a string of VQ codes or acoustic features. Speech recognition algorithms typically take advantage of the fact that the probability of a word, given a sequence of VQ codes, can be calculated