Automatic assessment of phonological processes

• US 7,302,389 B2
• Filed: 08/08/2003
• Issued: 11/27/2007
• Est. Priority Date: 05/14/2003
• Status: Active Grant

• Current Assignee: WSOU Investments, LLC (WSOU Holdings, LLC)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Vinchhi, Chetan, Raghavan, Prabhu, Gupta, Sunil K.
• Primary Examiner(s): Chawan, Vijay
• Application Number:
  US10/637,235
• Publication Number:
  US 20040230430A1
• Time in Patent Office: 1,572 Days
• Field of Search: 704/235, 704/260, 704/270, 704/244, 704/243, 704/257, 704/250
• US Class Current: 704/235
• CPC Class Codes: G09B 19/06 Foreign languages with audible presentation of material to be studied G09B5/04
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit

Abstract

A computer-based system generates alternative phonetic transcriptions for a target word or phrase corresponding to specific phonological processes that replace individual phonemes or clusters of two or more phonemes with replacement phonemes. The system compares a user'"'"'s speech with a list of possible transcriptions that includes the base (i.e., correct) transcription of the test target as well as the different alternative transcriptions, to identify the transcription that best matches the user'"'"'s. In a speech therapy application, the system identifies the phonological process(es), if any, associated with the user'"'"'s speech and generates statistics over multiple test targets that can be used to diagnose the user'"'"'s specific phonological disorders. The system can also be implemented in other contexts such as foreign language instruction and automated attendant applications to cover a wide variety and range of accents and/or phonological disorders.

Claims

1. A computer system comprising:

(a) an alternative pronunciation (AP) generator adapted to (1) identify one or more phonological processes for one or more base phonemes/clusters in a target, (2) select one or more replacement phonemes/clusters corresponding to the one or more identified phonological processes, and (3) generate one or more alternative transcriptions for the target from different combinations of the one or more base phonemes/clusters in the target and the one or more replacement phonemes/clusters;

(b) a speech recognition (SR) engine adapted to (1) compare a user'"'"'s speech for the target to a list of possible transcriptions including a base transcription for the target and the one or more alternative transcriptions and (2) identify a transcription in the list that best matches the user'"'"'s speech; and

(c) a score management (SM) module adapted to characterize the identified transcription to identify one or more phonological processes, if any, associated with the user'"'"'s speech.

2. The invention of claim 1, wherein the SM module is further adapted to compile statistics on the phonological processes associated with a plurality of targets for use in diagnosing one or more phonological disorders of the user.

3. The invention of claim 2, wherein the SM module is further adapted to generate a diagnosis of a phonological disorder for the user.

4. The invention of claim 1, wherein the SM module aligns the identified transcription with the base transcription to identify the one or more phonological processes associated with the user'"'"'s speech.

5. The invention of claim 1, further comprising a pronunciation evaluation module adapted to characterize quality of the user'"'"'s speech.

6. The invention of claim 1, wherein the SM module is adapted to recognize text associated with the identified transcription.

7. The invention of claim 1, wherein at least one of the alternative transcriptions corresponds to an interacting/ordered phonological process associated with a single base phoneme/cluster in the target.

8. The invention of claim 1, wherein at least one of the alternative transcriptions corresponds to two or more phonological processes associated with two or more different base phonemes/clusters in the target.

9. The invention of claim 1, wherein the SR engine compares the user'"'"'s speech to the list of possible transcriptions in a parametric domain.

10. The invention of claim 9, wherein the AP generator generates the alternative transcriptions in a text domain.

11. The invention of claim 10, wherein the SR engine converts the list of possible transcriptions from the text domain to the parametric domain using a database of phoneme templates that contains a mapping of each different phoneme from the text domain to the parametric domain.

12. The invention of claim 1, wherein, to identify the one or more phonological processes for the one or more base phonemes/clusters in the target, the AP generator is adapted to access a look-up table that contains one or more phonemes/clusters that can be modified as a result of each of a plurality of specified phonological processes and the corresponding replacement phoneme/cluster.

13. A computer-based method comprising:

(a) identifying one or more phonological processes for one or more base phonemes/clusters in a target;

(b) selecting one or more replacement phonemes/clusters corresponding to the one or more identified phonological processes;

(c) generating one or more alternative transcriptions for the target from different combinations of the one or more base phonemes/clusters in the target and the one or more replacement phonemes/clusters;

(d) comparing a user'"'"'s speech for the target to a list of possible transcriptions including a base transcription for the target and the one or more alternative transcriptions in order to identify a transcription in the list that best matches the user'"'"'s speech; and

(e) characterizing the identified transcription to identify one or more phonological processes, if any, associated with the user'"'"'s transcription.

14. The invention of claim 13, further comprising compiling statistics on the phonological processes associated with a plurality of targets for use in diagnosing one or more phonological disorders of the user.

15. The invention of claim 14, further comprising generating a diagnosis of a phonological disorder for the user.

16. The invention of claim 13, wherein the identified transcription is characterized to recognize text associated with the identified transcription.

17. The invention of claim 13, wherein the user'"'"'s speech is compared to the list of possible transcriptions in a parametric domain.

18. The invention of claim 17, wherein:

the alternative transcriptions are generated in a text domain; and

the list of possible transcriptions are converted from the text domain to the parametric domain using a database of phoneme templates that contains a mapping of each different phoneme from the text domain to the parametric domain.

19. The invention of claim 13, wherein, to identify the one or more phonological processes for the one or more base phonemes/clusters in the target, step (a) comprises accessing a look-up table that contains one or more phonemes/clusters that can be modified as a result of each of a plurality of specified phonological processes and the corresponding replacement phoneme/cluster.

20. A computer-based method for generating one or more alternative transcriptions for a target comprising, for one or more base phonemes/clusters in the target:

(a) identifying one or more phonological processes for the one or more base phonemes/clusters in the target;

(b) selecting one or more replacement phonemes/clusters corresponding to the one or more identified phonological processes; and

(c) generating the one or more alternative transcriptions for the target from different combinations of the one or more base phonemes/clusters in the target and the one or more replacement phonemes/clusters.

21. The invention of claim 20, wherein at least one of the alternative transcriptions corresponds to an interacting/ordered phonological process associated with a single base phoneme/cluster in the target.

22. The invention of claim 20, wherein at least one of the alternative transcriptions corresponds to two or more phonological processes associated with two or more different base phonemes/clusters in the target.

23. The invention of claim 20, wherein, to identify the one or more phonological processes for the one or more base phonemes/clusters in the target, step (a) comprises accessing a look-up table that contains one or more phonemes/clusters that can be modified as a result of each of a plurality of specified phonological processes and the corresponding replacement phoneme/cluster.