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 system comprising:
a processor; and
a computer-readable storage medium having processor-executable instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
initiating a voice call with a remote application;
determining whether the remote application can apply standardized speech recognition models; and
when the remote application cannot apply standardized speech recognition models:
determining whether the remote application can apply transformations of a standard speech recognition model;
responsive to the remote application being able to apply transformations of a standard speech recognition model:
transmitting transformations of a generic model to the remote application; and
instructing the remote application to recognize speech based on the transmitted transformations.
2. The computer-implemented method of claim 1 , further comprising;
determining availability of supervised or unsupervised transformations; and
responsive to determining that supervised or unsupervised transformations are available, transmitted the supervised or unsupervised transformations to the remote application as the transformations of the generic model.
3. The computer-implemented method of claim 1 , further comprising:
responsive to the remote application not being able to apply transformations of a standard speech recognition model, instructing the remote application to recognize speech with the generic model.
4. The computer-implemented method of claim 1 , wherein the transmitting occurs using an edge device in a communications network.
5. The computer-implemented method of claim 1 , wherein the remote application is a game, and wherein the game identifies voice commands in recognized speech and controls elements of the game based on the voice commands.
6. The computer-implemented method of claim 1 , wherein the generic model is publicly available.
7. The computer-implemented method of claim 1 , wherein a network client authenticates the speech before instructing the remote application to recognize the speech.
8. A computer-implemented method comprising:
initiating a voice call with a remote application;
determining, by processor-executable instructions executed by a processor, whether the remote application can apply standardized speech recognition models; and
when the remote application cannot apply standardized speech recognition models:
the processor-executable instructions when executed by the processor determining whether the remote application can apply transformations of a standard speech recognition model;
responsive to the remote application being able to apply transformations of a standard speech recognition model:
transmitting transformations of a generic model to the remote application; and
instructing the remote application to recognize speech based on the transmitted transformations.
9. The computer-implemented method of claim 8 , further comprising;
determining availability of supervised or unsupervised transformations; and
responsive to determining that supervised or unsupervised transformations are available, transmitted the supervised or unsupervised transformations to the remote application as the transformations of the generic model.
10. The computer-implemented method of claim 8 , further comprising:
responsive to the remote application not being able to apply transformations of a standard speech recognition model, instructing the remote application to recognize speech with the generic model.
11. The computer-implemented method of claim 8 , wherein the transmitting occurs using an edge device in a communications network.
12. The computer-implemented method of claim 8 , wherein the remote application is a game, and wherein the game identifies voice commands in recognized speech and controls elements of the game based on the voice commands.
13. The computer-implemented method of claim 8 , wherein the generic model is publicly available.
14. The computer-implemented method of claim 8 , wherein a network client authenticates the speech before instructing the remote application to recognize the speech.
15. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
initiating a voice call with a remote application;
determining whether the remote application can apply standardized speech recognition models; and
when the remote application cannot apply standardized speech recognition models:
determining whether the remote application can apply transformations of a standard speech recognition model;
responsive to the remote application being able to apply transformations of a standard speech recognition model:
transmitting transformations of a generic model to the remote application; and
instructing the remote application to recognize speech based on the transmitted transformations.
16. The computer-implemented method of claim 15 , further comprising;
determining availability of supervised or unsupervised transformations; and
responsive to determining that supervised or unsupervised transformations are available, transmitted the supervised or unsupervised transformations to the remote application as the transformations of the generic model.
17. The computer-implemented method of claim 15 , further comprising:
responsive to the remote application not being able to apply transformations of a standard speech recognition model, instructing the remote application to recognize speech with the generic model.
18. The computer-implemented method of claim 15 , wherein the transmitting occurs using an edge device in a communications network.
19. The computer-implemented method of claim 15 , wherein the remote application is a game, and wherein the game identifies voice commands in recognized speech and controls elements of the game based on the voice commands.
20. The computer-implemented method of claim 15 , wherein the generic model is publicly available.