Segmentation technique increasing the active vocabulary of speech recognizers

• US 6,738,741 B2
• Filed: 11/18/2002
• Issued: 05/18/2004
• Est. Priority Date: 08/28/1998
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Emam, Ossama, Kunzmann, Siegfried
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Lerner, Martin
• Application Number:
  US10/298,494
• Publication Number:
  US 20030078778A1
• Time in Patent Office: 547 Days
• Field of Search: 704/231, 704/240, 704/251, 704/252, 704/254, 704/255, 704/257, 704/9
• US Class Current: 704/251
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A speech recognition system and a method executed by a speech recognition system focusing on the vocabulary of the speech recognition system and its usage during the speech recognition process is provided. A segmented vocabulary and its exploitation is provided comprising a multitude of entries wherein an entry is either identical to a legal word or a constituent of a legal word of the language, and the constituent is an arbitrary sub-component of the legal word according to the orthography. A constituent can comprise any number of characters not limited to a syllable of a legal word or a recognition unit of the speech recognition system. The vocabulary is used to recognize constituents of the vocabulary for recombination of the constituents into legal words if a constituent combination table indicates that the recognized constituents are a legal concatenation in the language.

Claims

1. A speech recognition system for recognition of spoken speech of a language, the speech recognition system comprising:

a vocabulary including a multitude of words of said language recognizable by said speech recognition system, the vocabulary comprising entries identical to legal words of said language and entries that are constituents of legal words of said language, said constituents being arbitrary sub-components of said legal words according to their orthography, wherein said constituents are selected to achieve a compression of said vocabulary, wherein said vocabulary defines legal words of said language recognizable by said speech recognition system either by an entry itself, or by legal recombination of up to S entries in combination representing a legal word of said language; and

a constituent-combination-table indicating which concatenations of said constituents are legal concatenations in said language;

wherein said constituent-combination-table comprises, in the case of S =2 or S =3, at least one of;

a core-prefix-matrix indicating whether a combination of a prefix-constituent and a core-constituent is a legal combination in said language or not;

a prefix-suffix-matrix indicating whether a combination of a prefix-constituent and a suffix-constituent is a legal combination in said language or not; and

a prefix-prefix-matrix indicating whether a combination of a first-prefix-constituent and a second-prefix-constituent is a legal combination in said language building a third-prefix-constituent or not.

2. A speech recognition system according to claim 1, wherein S is 2 or 3.

3. A speech recognition system according to claim 2, wherein said vocabulary comprises, if S is 2, constituents allowing for recombination of legal words from a prefix-constituent and a core-constituent, or from a core-constituent and a suffix-constituent, or from a prefix-constituent and a suffix-constituent and further wherein said vocabulary comprises, if S is 3, constituents allowing for recombination of legal words from a prefix-constituent, a core-constituent and a suffix-constituent.

4. A speech recognition system according to claim 1, further wherein for at least one of said core-prefix-matrix, said prefix-suffix-matrix, said prefix-prefix-matrix, said core-constituents, said prefix-constituents and said suffix-constituents are assigned unique numbers forming the indexes of said matrixes.

5. A speech recognition system according to claim 4, further comprising a post-processor responsive to an input comprising recognized constituents of said vocabulary for recombination of said constituents into legal words of said language exploiting said constituent-combination-table.

6. A speech recognition system according to claim 5, further wherein said post-processor is at least one of:

(a) responsive to two consecutive constituents representing a first prefix-constituent and a second prefix-constituent by one of;

recombining said first prefix-constituent and said second prefix-constituent into a third prefix-constituent if said prefix-prefix-matrix is indicating said first prefix-constituent and said second prefix-constituent as a legal combination in said language, and

dropping said first prefix-constituent if said prefix-prefix-matrix is indicating said first prefix-constituent and said second prefix-constituent as an illegal combination in said language;

(b) responsive to two consecutive constituents representing a prefix-constituent and a core-constituent by one of;

recombining said prefix-constituent and said core-constituent into a second core-constituent if said core-prefix-matrix is indicating said prefix-constituent and said core-constituent as a legal combination in said language, and

if said core-prefix-matrix is indicating said prefix-constituent and said core-constituent as an illegal combination in said language, by replacing said prefix-constituent with an alternative prefix-constituent and recombining said alternative prefix-constituent and said core-constituent if said core-prefix-matrix is indicating said alternative prefix-constituent and said core-constituent as a legal combination in said language; and

(c) responsive to two consecutive constituents representing a prefix-constituent and a suffix-constituent by;

recombining said prefix-constituent and said suffix-constituent into a second prefix-constituent if said prefix-suffix-matrix is indicating said prefix-constituent and said suffix-constituent as a legal combination in said language.

7. A speech recognition system according to claim 6, further comprising at least one of the step of:

not recombining said prefix-constituent and said suffix-constituent and treating said prefix-constituent as a separate entry if said prefix-suffix-matrix is indicating said prefix-constituent and said suffix-constituent as an illegal combination in said language.

8. A speech recognition system according to claim 6, further wherein said alternative prefix-constituent is retrieved from an alternative-list, said alternative-list comprising alternative prefix-constituents to said prefix-constituents in decreasing matching probability.

9. A speech recognition system according to claim 1, further comprising a language-model of said language being computed based on the N-gram frequencies of a sequence of N entries of said vocabulary.

10. A speech recognition system according to claim 1, wherein phones are used as smallest recognition units.

11. A method for use with a speech recognition system for recognition of spoken speech of a language, said method using a vocabulary including a multitude of words of said language recognizable by said speech recognition system, said method comprising the steps of:

identifying, in said spoken speech, entries of said vocabulary wherein the entries of said vocabulary comprise entries identical to legal words of said language and entries that are constituents of legal words of said language, said constituents being arbitrary sub-components of said legal words according to their orthography, wherein said constituents are selected to achieve a compression of said vocabulary; and

post-processing an input comprising recognized constituents of said vocabulary for recombination of said constituents into legal words, said post-processing-step recombining up to S constituents if a constituent-combination-table indicates that said recognized constituents are a legal concatenation in said language;

wherein the post-processing step further comprises at least one of;

(a) recombining two consecutive constituents representing a first-prefix-constituent and a second-prefix-constituent by one of;

recombining said first prefix-constituent and said second prefix-constituent into a third prefix-constituent if a prefix-prefix-matrix is indicating said first prefix-constituent and said second prefix-constituent as a legal combination in said language, and

dropping said first prefix-constituent if said prefix-prefix-matrix indicating said first prefix-constituent and said second prefix-constituent as an illegal combination in said language;

(b) recombining two consecutive constituents representing a prefix-constituent and a core-constituent by one of;

recombining said prefix-constituent and said core-constituent into a second core-constituent if a core-prefix-matrix is indicating said prefix-constituent and said core-constituent as a legal combination in said language, and

if said core-prefix-matrix is indicating said prefix-constituent and said core-constituent as an illegal combination in said language, replacing said prefix-constituent with an alternative prefix-constituent and recombining said alternative prefix-constituent and said core-constituent if said core-prefix-matrix is indicating said alternative prefix-constituent and said core-constituent as a legal combination in said language; and

(c) recombining two consecutive constituents representing a prefix-constituent and a suffix-constituent by recombining said prefix-constituent and said suffix-constituent into a second prefix-constituent if a prefix-suffix-matrix is indicating said prefix-constituent and said suffix-constituent as a legal combination in said language.

12. A method according to claim 11, wherein S is 2 or 3.

13. A method according to claim 12, wherein the post-processing step further comprises:

recombining, if S is 2, legal words from a prefix-constituent and a core-constituent, or from a core-constituent and a suffix-constituent, or from a prefix-constituent and a suffix-constituent, and recombining, if S is 3, legal words from a prefix-constituent, a core-constituent and a suffix-constituent.

14. A method according to claim 11, further comprising:

not recombining said prefix-constituent and said suffix-constituent and treating said prefix-constituent as a separate entry if said prefix-suffix-matrix is indicating said prefix-constituent and said suffix-constituent as an illegal combination in said language.

15. A method according to claim 11, wherein said alternative prefix-constituent is retrieved from an alternative-list, said alternative-list comprising alternative prefix-constituents to said prefix-constituents in decreasing matching probability.

16. A method according to claim 11, wherein the post-processing step further comprises:

assigning said core-constituents, said prefix-constituents and said suffix-constituents unique numbers used as indexes of said core-prefix-matrix and/or said prefix-suffix-matrix and/or said prefix-prefix-matrix.

17. A method according claim 11, further comprising the step of using a language-model of said language being based on the N-gram frequencies of a sequence of N entries of said vocabulary.

18. An article of manufacture for use with a speech recognition system for recognition of spoken speech of a language, said article of manufacture using a vocabulary including a multitude of words of said language recognizable by said speech recognition system, the article of manufacture comprising a machine readable medium containing one or more programs which when executed implement the step of:

identifying, in said spoken speech, entries of said vocabulary wherein the entries of said vocabulary comprise entries identical to legal words of said language and entries that are constituents of legal words of said language, said constituents being arbitrary sub-components of said legal words according to their orthography, wherein said constituents are selected to achieve a compression of said vocabulary; and

post-processing an input comprising recognized constituents of said vocabulary for recombination of said constituents into legal words, said post-processing-step recombining up to S constituents if a constituent-combination-table indicates that said recognized constituents are a legal concatenation in said language;

wherein the post-processing step further comprises at least one of;

(a) recombining two consecutive constituents representing a first-prefix-constituent and a second-prefix-constituent by one of;

recombining said first prefix-constituent and said second prefix-constituent into a third prefix-constituent if a prefix-prefix-matrix is indicating said first prefix-constituent and said second prefix-constituent as a legal combination in said language, and

dropping said first prefix-constituent if said prefix-prefix-matrix indicating said first prefix-constituent and said second prefix-constituent as an illegal combination in said language;

(b) recombining two consecutive constituents representing a prefix-constituent and a core-constituent by one of;

recombining said prefix-constituent and said core-constituent into a second core-constituent if a core-prefix-matrix is indicating said prefix-constituent and said core-constituent as a legal combination in said language, and

if said core-prefix-matrix is indicating said prefix-constituent and said core-constituent as an illegal combination in said language, replacing said prefix-constituent with an alternative prefix-constituent and recombining said alternative prefix-constituent and said core-constituent if said core-prefix-matrix is indicating said alternative prefix-constituent and said core-constituent as a legal combination in said language; and

(c) recombining two consecutive constituents representing a prefix-constituent and a suffix-constituent by recombining said prefix-constituent and said suffix-constituent into a second prefix-constituent if a prefix-suffix-matrix is indicating said prefix-constituent and said suffix-constituent as a legal combination in said language.

19. A speech recognition system for recognizing spoken speech of a language, the speech recognition system comprising:

a vocabulary including a multitude of words of said language recognizable by said speech recognition system, the vocabulary comprising a multitude of entries wherein said multitude of entries comprises entries identical to legal words of said language and entries that are constituents of legal words of said language, said constituents being arbitrary sub-components of said legal words according to its orthography;

wherein said vocabulary defines legal words of said language recognizable by said speech recognition system either by an entry itself, or by legal recombination of up to S entries in combination representing a legal word of said language;

a constituent-combination table indicating which concatenations of said legal constituents are legal concatenations in said language;

wherein said constituent-combination table comprises, in the case of S=2 or S=3, at least one of;

a core-prefix-matrix indicating whether a combination of a prefix-constituent and a core-constituent is a legal combination in said language or not;

a prefix-suffix-matrix indicating whether a combination of a prefix-constituent and a suffix-constituent is a legal combination in said language or not; and

a prefix-prefix-matrix indicating whether a combination of a first prefix-constituent and a second prefix-constituent is a legal combination in said language building a third prefix-constituent or not;

wherein for at least one of said core-prefix-matrix, said prefix-suffix-matrix, said prefix-prefix-matrix, said core-constituents, said prefix-constituents and said suffix-constituents are represented by unique numbers forming indexes of said matrices; and

a post-processor responsive to an input comprising recognized constituents of said vocabulary for recombination of said constituents into legal words of said language exploiting said constituent-combination table;

wherein said post-processor is at least one of;

(a) responsive to two consecutive constituents representing a first prefix-constituent and a second prefix-constituent by one of;

recombining said first prefix-constituent and said second prefix-constituent into a third prefix-constituent if said prefix-prefix-matrix is indicating said first prefix-constituent and said second prefix-constituent as a legal combination in said language, and

dropping said first prefix-constituent if said prefix-prefix-matrix is indicating said first prefix-constituent and said second prefix-constituent as an illegal combination in said language;

(b) responsive to two consecutive constituents representing a prefix-constituent and a core-constituent by one of;

recombining said prefix-constituent and said core-constituent into a second core-constituent if said core-prefix-matrix is indicating said prefix-constituent and said core-constituent as a legal combination in said language, and

if said core-prefix-matrix is indicating said prefix-constituent and said core-constituent as an illegal combination in said language, replacing said prefix-constituent with an alternative prefix-constituent and recombining said alternative prefix-constituent and said core-constituent if said core-prefix-matrix is indicating said alternative prefix-constituent and said core-constituent as a legal combination in said language; and

(c) responsive to two consecutive constituents representing a prefix-constituent and a suffix-constituent by;

recombining said prefix-constituent and said suffix-constituent into a second prefix-constituent if said prefix-suffix-matrix is indicating said prefix-constituent and said suffix-constituent as a legal combination in said language.