| 摘要 |
A computer system for converting a text message into an audio representation, including a text to speech converter and a text reader control procedure. A classifier procedure, called by the control procedure, classifies each word in the text message with regard to syntax, punctuation and membership in predefined classes of words, the predefined classes of words including numbers, measurement units, geographic designations, and date/time values. The classifier procedure generates classification values for each of the words in the text message. An abbreviation expanding procedure, called by the control procedure after execution of the classifier procedure, identifies abbreviation words in the text message that match predefined abbreviations and identifies a set of potential expansion values for each identified abbreviation word. The abbreviation expanding procedure evaluates, based on the classification values for words neighboring the identified words, which, if any, of the potential expansion values is applicable, and substitutes the potential expansion value for the identified abbreviation word when the evaluation yields a success value. An acronym/initialism expanding procedure identifies words in the text message that are acronyms and initialisms, parses pronounceable syllables within the identified words and generates a substitute string in the form of a sequence of units. Each unit in the generated sequence is a letter, number, pronounceable syllable or a multiple letter identifier. The control procedure passes to the text to speech converter for each word in the text message (A) the expansion value, if any, generated by the abbreviation expanding procedure, (B) the substitute string, if any, generated by the acronym/initialism expanding procedure, and otherwise (C) the word.
|
