Automatic assessment of phonological processes

• US 20040230430A1
• Filed: 08/08/2003
• Published: 11/18/2004
• 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: Gupta, Sunil K., Raghavan, Prabhu, Vinchhi, Chetan
• Granted Patent: US 7,302,389 B2
• Time in Patent Office: Days
• 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 generate one or more alternative transcriptions for a target; and

(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.

2. The invention of claim 1, further comprising a score management (SM) module adapted to characterize the identified transcription.

3. The invention of claim 2, wherein the SM module is adapted to identify one or more phonological processes, if any, associated with the user'"'"'s speech.

4. The invention of claim 3, 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.

5. The invention of claim 4, wherein the SM module is further adapted to generate a diagnosis of a phonological disorder for the user.

6. The invention of claim 3, 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.

7. The invention of claim 2, further comprising a pronunciation evaluation module adapted to characterize quality of the user'"'"'s speech.

8. The invention of claim 2, wherein the SM module is adapted to recognize text associated with the identified transcription.

9. The invention of claim 1, wherein, for one or more base phonemes/clusters in the target, the AP generator (1) selects one or more replacement phonemes/clusters corresponding to one or more phonological processes and (2) generates the one or more alternative transcriptions from different combinations of base phonemes/clusters and replacement phonemes/clusters.

10. The invention of claim 9, 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.

11. The invention of claim 9, 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.

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

13. The invention of claim 12, wherein the AP generator generates the alternative transcriptions in a text domain.

14. The invention of claim 13, 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.

15. A computer-based method comprising:

(a) generating one or more alternative transcriptions for a target; and

(b) 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.

16. The invention of claim 15, further comprising:

(c) characterizing the identified transcription.

17. The invention of claim 16, wherein the identified transcription is characterized to identify one or more phonological processes, if any, associated with the user'"'"'s transcription.

18. The invention of claim 17, 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.

19. The invention of claim 18, further comprising generating a diagnosis of a phonological disorder for the user.

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

21. The invention of claim 15, wherein, for one or more base phonemes/clusters in the target, generating the one or more alternative transcriptions comprises (1) selecting one or more replacement phonemes/clusters corresponding to one or more phonological processes and (2) generating the one or more alternative transcriptions from different combinations of base phonemes/clusters and replacement phonemes/clusters.

22. The invention of claim 15, wherein the user'"'"'s speech is compared to the list of possible transcriptions in a parametric domain.

23. The invention of claim 22, 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.

24. 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:

selecting one or more replacement phonemes/clusters corresponding to one or more phonological processes; and

generating the one or more alternative transcriptions from different combinations of base phonemes/clusters and replacement phonemes/clusters.

25. The invention of claim 24, 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.

26. The invention of claim 24, 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.