System and method for standardized speech recognition infrastructure
View Patent ↗Disclosed herein are systems, methods, and computer-readable storage media for selecting a speech recognition model in a standardized speech recognition infrastructure. The system receives speech from a user, and if a user-specific supervised speech model associated with the user is available, retrieves the supervised speech model. If the user-specific supervised speech model is unavailable and if an unsupervised speech model is available, the system retrieves the unsupervised speech model. If the user-specific supervised speech model and the unsupervised speech model are unavailable, the system retrieves a generic speech model associated with the user. Next the system recognizes the received speech from the user with the retrieved model. In one embodiment, the system trains a speech recognition model in a standardized speech recognition infrastructure. In another embodiment, the system handshakes with a remote application in a standardized speech recognition infrastructure.
1. A method comprising:
receiving speech from a user;
determining, via a processor, to apply one of supervised training and unsupervised training; and
when supervised training is selected:
determining whether available data are sufficient to build a new speech recognition model;
when the available data is sufficient to build the new speech recognition model, building the new speech recognition model using the available data; and
when the available data is not sufficient to build the new speech recognition model:
selecting an existing speech recognition model; and
generating an adapted speech recognition model based on transformations generated from the existing speech recognition model based on the speech and associated transcriptions.
2. The method of claim 1 , wherein the new speech recognition model, the existing speech recognition model and the adapted speech recognition model are standardized speech models.
3. The method of claim 1 , wherein one of the new speech recognition model, the existing speech recognition model and the adapted speech recognition model is publicly available.
4. The method of claim 1 , wherein the existing speech recognition model is a general model and wherein the adapted speech recognition model is a result of applying transformations to the existing speech recognition model.
5. The method of claim 1 , further comprising recognizing additional speech using the adapted speech recognition model.
6. The method of claim 5 , wherein recognizing the additional speech is performed off-line at a later time.
7. The method of claim 1 , further comprising reusing speech models for additional received speech.
8. The method of claim 1 , further comprising:
recognizing voice commands in the speech; and
controlling elements of a game based on the voice commands.
9. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored, which, when executed by the processor, result in the processor performing operations comprising:
receiving speech from a user;
determining, via a processor, to apply one of supervised training and unsupervised training; and
when supervised training is selected:
determining whether available data are sufficient to build a new speech recognition model;
when the available data is sufficient to build the new speech recognition model, building the new speech recognition model using the available data; and
when the available data is not sufficient to build the new speech recognition model:
selecting an existing speech recognition model; and
generating an adapted speech recognition model based on transformations generated from the existing speech recognition model based on the speech and associated transcriptions.
10. The system of claim 9 , wherein the new speech recognition model, the existing speech recognition model and the adapted speech recognition model are standardized speech models.
11. The system of claim 9 , wherein one of the new speech recognition model, the existing speech recognition model and the adapted speech recognition model is publicly available.
12. The system of claim 9 , wherein the existing speech recognition model is a general model and wherein the adapted speech recognition model is a result of applying transformations to the existing speech recognition model.
13. The system of claim 9 , the computer-readable storage medium having additional instructions stored which result in the operations further comprising recognizing additional speech using the adapted speech recognition model.
14. The system of claim 13 , wherein recognizing the additional speech is performed off-line at a later time.
15. The system of claim 9 , the computer-readable storage medium having additional instructions stored which result in the operations further comprising reusing speech models for additional received speech.
16. The system of claim 9 , the computer-readable storage medium having additional instructions stored which result in the operations further comprising:
recognizing voice commands in the speech; and
controlling elements of a game based on the voice commands.
17. A non-transitory computer-readable storage device having instructions stored, which, when executed by a computing device, result in the computing device performing operations comprising:
receiving speech from a user;
determining, via a processor, to apply one of supervised training and unsupervised training; and
when supervised training is selected:
determining whether available data are sufficient to build a new speech recognition model;
when the available data is sufficient to build the new speech recognition model, building the new speech recognition model using the available data; and
when the available data is not sufficient to build the new speech recognition model:
selecting an existing speech recognition model; and
generating an adapted speech recognition model based on transformations generated from the existing speech recognition model based on the speech and associated transcriptions.
18. The non-transitory computer-readable storage device of claim 17 , wherein the new speech recognition model, the existing speech recognition model and the adapted speech recognition model are standardized speech models.
19. The non-transitory computer-readable storage device of claim 17 , wherein one of the new speech recognition model, the existing speech recognition model and the adapted speech recognition model is publicly available.
20. The computer-readable storage medium of claim 17 , wherein the existing speech recognition model is a general model and wherein the adapted speech recognition model is a result of applying transformations to the existing speech recognition model.