Abbreviation and acronym/initialism expansion procedures for a text to speech reader

• US 5,634,084 A
• Filed: 01/20/1995
• Issued: 05/27/1997
• Est. Priority Date: 01/20/1995
• Status: Expired due to Fees

• Current Assignee: ScanSoft, Inc. n/k/a Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Centigram Communications Corporation (TE Connectivity Limited)
• Inventors: Malsheen, Bathsheba J., Disner, Sandra F., Groner, Gabriel F.
• Primary Examiner(s): MacDonald, Allen R.
• Assistant Examiner(s): Mattson, Robert
• Application Number:
  US08/376,732
• Time in Patent Office: 858 Days
• Field of Search: 395/2.2, 395/2.69, 381/51, 381/52
• US Class Current: 704/260
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

An improved text-to-speech synthesizer that employs a text to speech converter, a text reader control procedure, a classifier procedure, an abbreviation expansion procedure, and an acronym/initialism expanding procedure is herein described. A classifier procedure is used to classify generate classification values for each word in the text message with regard to syntax, punctuation and membership in predefined classes of words, the predefined classes of words including number, measurement units, geographic designations, and date/time values. An abbreviation expansion 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 for the identified abbreviation word when 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 that can consist of any combination of letters, numbers, pronounceable syllables or multiple letter identifiers.

Claims

1. A computer system for converting a text message into audio signals, including:

a text to speech converter that translates text into audio signals;

a text reader control procedure for receiving said text message, said text message having a sequence of words;

a classifier procedure, coupled to said text reader control procedure, that classifies specified words in said text message with regard to syntax, punctuation and membership in predefined classes of words, said predefined classes of words including numbers, measurement units, geographic designations, and date/time values;

said classifier procedure generating classification values for said words in said text message; and

an abbreviation expanding procedure that receives said classification values and said text message, identifies abbreviation words in said text message that match predefined abbreviations and identifying a set of potential expansion values for each said identified abbreviation word, evaluates based on said classification values for words neighboring said identified words and in accordance with a predefined set of rules which, if any, of said potential expansion values is applicable, and substituting said potential expansion value for said identified abbreviation word when said evaluation yields a success value;

wherein said text reader control procedure includes instructions for receiving expansion values from said abbreviation expanding procedure, and passing to said text to speech converter for each word in said text message said expansion value, if any, generated by said abbreviation expanding procedure for said word.

5. The computer system of claim 1,

an abbreviation dictionary having, for each of a plurality of predefined abbreviations, one or more abbreviation expansion entries, each abbreviation expansion entry indicating one said potential expansion value associated with a particular one of said predefined abbreviations and indicating one of said predefined set of rules for determining the applicability of said potential expansion value;

said abbreviation expanding procedure including instructions for evaluating each said identified potential expansion value for each said identified abbreviation word by executing said rule indicated in the corresponding abbreviation expansion entry in said abbreviation dictionary, and selecting said identified potential expansion value as a substitution value for said identified abbreviation word when said executed rule returns a predefined value indicating applicability of said identified potential expansion value.

2. A computer system for converting a text message into audio signals, including:

a text to speech converter that translates text into audio signals;

a text reader control procedure for receiving said text message, said text message having a sequence of words;

an acronym/initialism expanding procedure, coupled to said text reader control procedure, that identifies words in said text message that are acronyms and initialisms, parsing pronounceable syllables within said identified words and generating a substitute string comprising a sequence of units, each unit selected from the set consisting of a letter, number, pronounceable syllable and multiple letter identifier;

said acronym/initialism expanding procedure including instructions for separating pronounceable syllables and individual letters not pronounceable as syllables from an identified word in said text message in accordance with predefined word parsing criteria;

wherein said text reader control procedure includes instructions for receiving said substitute strings from said acronym/initialism expanding procedure, and passing to said text to speech converter for each word in said text message said substitute string, if any, generated by said acronym/initialism expanding procedure.

3. A computer system for converting a text message into audio signals, including:

a text to speech converter that translates text into audio signals;

a text reader control procedure for receiving said text message, said text message having a sequence of words;

a classifier procedure, coupled to said text reader control procedure, that classifies specified words in said text message with regard to syntax, punctuation and membership in predefined classes of words, said predefined classes of words including numbers, measurement units, geographic designations, and date/time values;

said classifier procedure generating classification values for said words in said text message;

an abbreviation expanding procedure that receives said classification values and said text message, identifies abbreviation words in said text message that match predefined abbreviations and identifying a set of potential expansion values for each said identified abbreviation word, evaluates based on said classification values for words neighboring said identified words which, if any, of said potential expansion values is applicable, and substituting said potential expansion value for said identified abbreviation word when said evaluation yields a success value; and

an acronym/initialism expanding procedure, coupled to said classifier procedure, that identifies words in said text message that are acronyms and initialisms, parsing pronounceable syllables within said identified words and generating a substitute string comprising a sequence of units, each unit selected from the set consisting of a letter, number, pronounceable syllable and multiple letter identifier;

said acronym/initialism expanding procedure including instructions for separating pronounceable syllables and individual letters not pronounceable as syllables from an identified word in said text message in accordance with predefined word parsing criteria;

wherein said text reader control procedure includes instructions for receiving expansion values from said abbreviation expanding procedure and said substitute strings from said acronym/initialism expanding procedure, and passing to said text to speech converter for each word in said text message (A) said expansion value, if any, generated by said abbreviation expanding procedure for said word, (B) said substitute string, if any, generated by said acronym/initialism expanding procedure, and (C) said word otherwise.

4. The computer system of claim 3,

an abbreviation dictionary having, for each of a plurality of predefined abbreviations, one or more abbreviation expansion entries, each abbreviation expansion entry indicating one said potential expansion value associated with a particular one of said predefined abbreviations and indicating one of said predefined set of rules for determining the applicability of said potential expansion value;

said abbreviation expanding procedure including instructions for evaluating each said identified potential expansion value for each said identified abbreviation word by executing said rule indicated in the corresponding abbreviation expansion entry in said abbreviation dictionary, and selecting said identified potential expansion value as a substitution value for said identified abbreviation word when said executed rule returns a predefined value indicating applicability of said identified potential expansion value.

6. A memory for storing data for access by programs being executed on a data processing system, said memory comprising:

a text to speech converter that translates text into audio signals;

a text reader control procedure for receiving said text message, said text message having a sequence of words;

a classifier procedure, coupled to said text reader control procedure, that classifies specified words in said text message with regard to syntax, punctuation and membership in predefined classes of words, said predefined classes of words including numbers, measurement units, geographic designations, and date/time values;

said classifier procedure generating classification values for said words in said text message; and

an abbreviation expanding procedure that receives said classification values and said text message, identifies abbreviation words in said text message that match predefined abbreviations and identifying a set of potential expansion values for each said identified abbreviation word, evaluates based on said classification values for words neighboring said identified words and in accordance with a predefined set of rules which, if any, of said potential expansion values is applicable, and substituting said potential expansion value for said identified abbreviation word when said evaluation yields a success value;

wherein said text reader control procedure includes instructions for receiving expansion values from said abbreviation expanding procedure, and passing to said text to speech converter for each word in said text message said expansion value, if any, generated by said abbreviation expanding procedure for said word.

7. The memory of claim 6,

an abbreviation dictionary having, for each of a plurality of predefined abbreviations, one or more abbreviation expansion entries, each abbreviation expansion entry indicating one said potential expansion value associated with a particular one of said predefined abbreviations and indicating one of said predefined set of rules for determining the applicability of said potential expansion value;

said abbreviation expanding procedure including instructions for evaluating each said identified potential expansion value for each said identified abbreviation word by executing said rule indicated in the corresponding abbreviation expansion entry in said abbreviation dictionary, and selecting said identified potential expansion value as a substitution value for said identified abbreviation word when said executed rule returns a predefined value indicating applicability of said identified potential expansion value.

8. The memory of claim 6,

further including an acronym/initialism expanding procedure, coupled to said classifier procedure, that identifies words in said text message that are acronyms and initialisms, parsing pronounceable syllables within said identified words and generating a substitute string comprising a sequence of units, each unit selected from the set consisting of a letter, number, pronounceable syllable and multiple letter identifier;

wherein said text reader control procedure includes instructions for receiving expansion values from said abbreviation expanding procedure and said substitute strings from said acronym/initialism expanding procedure, and passing to said text to speech converter for each word in said text message (A) said expansion value, if any, generated by said abbreviation expanding procedure for said word, (B) said substitute string, if any, generated by said acronym/initialism expanding procedure, and (C) said word otherwise.

9. A memory for storing data for access by programs being executed on a data processing system, said memory comprising:

a text to speech converter that translates text into audio signals;

a text reader control procedure for receiving said text message, said text message having a sequence of words;

an acronym/initialism expanding procedure, coupled to said text reader control procedure, that identifies words in said text message that are acronyms and initialisms, parsing pronounceable syllables within said identified words and generating a substitute string comprising a sequence of units, each unit selected from the set consisting of a letter, number, pronounceable syllable and multiple letter identifier;

said acronym/initialism expanding procedure including instructions for separating pronounceable syllables and individual letters not pronounceable as syllables from an identified word in said text message in accordance with predefined word parsing criteria;

wherein said text reader control procedure includes instructions for receiving said substitute strings from said acronym/initialism expanding procedure, and passing to said text to speech converter for each word in said text message said substitute string, if any, generated by said acronym/initialism expanding procedure.

10. A method of converting a text message into audio signals, comprising the steps of:

receiving said text message, said text message having a sequence of words;

classifying specified words in said text message with regard to syntax, punctuation and membership in predefined classes of words, said predefined classes of words including numbers, measurement units, geographic designations, and date/time values;

said classifying step generating classification values for said words in said text message; and

identifying abbreviation words in said text message that match predefined abbreviations and identifying a set of potential expansion values for each said identified abbreviation word;

evaluating based on said classification values for words neighboring said identified words and in accordance with a predefined set of rules which, if any, of said potential expansion values is applicable, and substituting in said received text message said potential expansion value for said identified abbreviation word when said evaluation yields a success value; and

translating said received text message with said substituted expansion values, if any, into audio signals.

11. The method of claim 10,

said abbreviation word identifying step including accessing an abbreviation dictionary having, for each of a plurality of predefined abbreviations, one or more abbreviation expansion entries, each abbreviation expansion entry indicating one said potential expansion value associated with a particular one of said predefined abbreviations and indicating one of said predefined set of rules for determining the applicability of said potential expansion value;

said abbreviation word identifying step further including evaluating each said identified potential expansion value for each said identified abbreviation word by executing said rule indicated in the corresponding abbreviation expansion entry in said abbreviation dictionary, and selecting said identified potential expansion value as a substitution value for said identified abbreviation word when said executed rule returns a predefined value indicating applicability of said identified potential expansion value.

12. The method of claim 10,

identifying words in said text message that are acronyms and initialisms, parsing pronounceable syllables within said identified words and generating a substitute string comprising a sequence of units, each unit selected from the set consisting of a letter, number, pronounceable syllable and multiple letter identifier;

said substitute string generating step including separating pronounceable syllables and individual letters not pronounceable as syllables from an identified word in said text message in accordance with predefined word parsing criteria;

said substituting step including substituting in said received text message for each word in said text, said substitute string, if any, generated by said acronyms and initialisms identifying, parsing and generating steps.

13. A method of converting a text message into audio signals, comprising the steps of:

receiving said text message, said text message having a sequence of words;

identifying words in said text message that are acronyms and initialisms, parsing pronounceable syllables within said identified words and generating a substitute string comprising a sequence of units, each unit selected from the set consisting of a letter, number, pronounceable syllable and multiple letter identifier;

said substitute string generating step including separating pronounceable syllables and individual letters not pronounceable as syllables from an identified word in said text message in accordance with predefined word parsing criteria;

substituting in said received text message for each word in said text, said substitute string, if any, generated by said acronyms and initialisms identifying, parsing and generating steps; and

translating said received text message with said substitute strings, if any, into audio signals.