Local and cloud speech recognition
Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for distributing the performance of speech recognition among a remote control device and a voice platform in the cloud. In some embodiments, the remote control device operates to receive a voice input from a user. The remote control device detects a trigger word in the voice input. The remote control device then processes the voice input. The remote control device then transmits the voice input to a voice platform based on the detecting in order to determine an intent associated with the voice input.
1 . A computer-implemented method for performing speech recognition, comprising:
receiving, by at least one computer processor, a voice input from a user;
detecting that a trigger word is in the voice input with a first confidence value;
determining the first confidence value is below a threshold value;
transmitting the voice input to a voice platform in response to the determination that the first confidence value is below the threshold value;
in response to the voice platform performing a secondary trigger word detection on the voice input, receiving a confirmation from the voice platform that the trigger word is in the voice input with a second confidence value; and
transmitting the voice input to the voice platform in response to the receiving the confirmation that the trigger word is in the voice input with the second confidence value.
2 . The computer-implemented method of claim 1 , further comprising:
performing echo cancellation on the voice input.
3 . The computer-implemented method of claim 1 , further comprising:
performing noise cancellation on the voice input using a position of the user, wherein the performing comprises adjusting a reception pattern for a microphone using the position of the user.
4 . The computer-implemented method of claim 1 , wherein the second confidence value is higher than the first confidence value.
5 . The computer-implemented method of claim 1 , wherein the transmitting the voice input to the voice platform in response to the receiving the confirmation that the trigger word is in the voice input with the second confidence value comprises:
transmitting a remainder of the voice input after the detected trigger word to the voice platform.
6 . The computer-implemented method of claim 1 , wherein the voice platform converts the voice input into a text input using automated speech recognition.
7 . The computer-implemented method of claim 1 , wherein the voice platform comprises a cloud computing platform.
8 . A system, comprising:
a microphone;
one or more memories; and
at least one processor each coupled to at least one of the memories and configured to perform operations comprising:
receiving a voice input from a user via the microphone;
detecting that a trigger word is in the voice input with a first confidence value;
determining the first confidence value is below a threshold value;
transmitting the voice input to a voice platform in response to the determination that the first confidence value is below the threshold value;
in response to the voice platform performing a secondary trigger word detection on the voice input, receiving a confirmation from the voice platform that the trigger word is in the voice input with a second confidence value; and
transmitting the voice input to the voice platform in response to the receiving the confirmation that the trigger word is in the voice input with the second confidence value.
9 . The system of claim 8 , wherein the operations further comprise:
performing echo cancellation on the voice input.
10 . The system of claim 8 , wherein the operations further comprise:
performing noise cancellation on the voice input using a position of the user, wherein the performing comprises adjusting a reception pattern for the microphone using the position of the user.
11 . The system of claim 8 , wherein the second confidence value is higher than the first confidence value.
12 . The system of claim 8 , wherein the transmitting the voice input to the voice platform in response to the receiving the confirmation that the trigger word is in the voice input with the second confidence value comprises:
transmitting a remainder of the voice input after the trigger word to the voice platform.
13 . The system of claim 8 , wherein the voice platform converts the voice input into a text input using automated speech recognition.
14 . The system of claim 8 , wherein the voice platform comprises a cloud computing platform.
15 . A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one computing device, cause the at least one computing device to perform operations comprising:
receiving a voice input from a user;
detecting that a trigger word is in the voice input with a first confidence value;
determining the first confidence value is below a threshold value;
transmitting the voice input to a voice platform in response to the determination that the first confidence value is below the threshold value;
in response to the voice platform performing a secondary trigger word detection on the voice input, receiving a confirmation from the voice platform that the trigger word is in the voice input with a second confidence value; and
transmitting the voice input to the voice platform in response to the receiving the confirmation that the trigger word is in the voice input with the second confidence value.
16 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:
performing echo cancellation on the voice input.
17 . The non-transitory computer-readable medium of claim 15 , the operations further comprising:
performing noise cancellation on the voice input using a position of the user, wherein the performing comprises adjusting a reception pattern for a microphone using the position of the user.
18 . The non-transitory computer-readable medium of claim 15 , wherein the second confidence value is higher than the first confidence value.
19 . The non-transitory computer-readable medium of claim 15 , wherein the transmitting the voice input to the voice platform in response to the receiving the confirmation that the trigger word is in the voice input with the second confidence value comprises:
transmitting a remainder of the voice input after the trigger word to the voice platform.
20 . The non-transitory computer-readable medium of claim 15 , wherein the voice platform converts the voice input into a text input using automated speech recognition.