Trigger word detection with multiple digital assistants
Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for selecting a digital assistant from among multiple digital assistants. An embodiment operates by receiving a voice input containing a trigger word at a first voice adapter associated with a digital assistant that generates a first confidence score for the trigger word. The embodiment further receives the voice input at a second voice adapter that generates a second confidence score for the trigger word. The embodiment determines the first confidence score is higher than the second confidence score. The embodiment selects the digital assistant based on the determining.
1. A computer implemented method for selecting a digital assistant, comprising:
first receiving, by at least one processor, a voice input at a first voice adapter;
calculating, by the at least one processor using the first voice adapter, a first confidence score that the voice input contains a first trigger word, wherein the first trigger word is mapped to a first digital assistant among a plurality of digital assistants stored in a voice platform;
second receiving, by the at least one processor, the voice input at a second voice adapter;
calculating, by the at least one processor using the second voice adapter, a second confidence score that the voice input contains a second trigger word, wherein the second trigger word is mapped to a second digital assistant, and the second trigger word is different from the first trigger word;
determining, by the at least one processor, the first confidence score is higher than the second confidence score; and
in response to the determining, transmitting, by the at least one processor, a request to the voice platform to select the first digital assistant from among the plurality of digital assistants stored in the voice platform.
2. The method of claim 1 , further comprising:
normalizing, by the at least one processor using the first voice adapter, the first confidence score based on a first confidence score criteria.
3. The method of claim 1 , further comprising:
determining, by the at least one processor, the first confidence score exceeds a threshold value.
4. The method of claim 1 , further comprising:
determining, by the at least one processor, that the first voice adapter generated the first confidence score within a timeout period.
5. The method of claim 1 , the determining further comprising:
determining, by the at least one processor, the first confidence score and the second confidence score are within an error range; and
determining, by the at least one processor, the first confidence score is higher than the second confidence score based on a priority criteria.
6. The method of claim 1 , the first receiving the voice input at the first voice adapter further comprising:
third receiving, by the at least one processor, the voice input from an audio responsive electronic device, wherein the audio responsive electronic device is configured to:
output a tone at a speaker;
determine an echo cancellation delay based on a time of receipt of the tone at a microphone; and
perform echo cancellation on the voice input based on the echo cancellation delay.
7. The method of claim 1 , the first receiving the voice input at the first voice adapter further comprising:
third receiving, by the at least one processor, the voice input from an audio responsive electronic device, wherein the audio responsive electronic device is configured to:
generate a first audio signal based on a tone and a second audio signal, wherein the generating distributes the tone across the second audio signal;
output the first audio signal at a speaker;
determine an echo cancellation delay based on a time of receipt of the tone in the first audio signal at a microphone; and
perform echo cancellation on the voice input based on the echo cancellation delay.
8. The method of claim 1 , further comprising:
outputting, by the at least one processor, an audio signal at a speaker in response to the determining, wherein the outputting comprises:
determining, by the at least one processor, a volume level of the audio signal;
modifying, by the at least one processor, the audio signal based on the volume level of the audio signal and a frequency response of the speaker; and
outputting, by the at least one processor, the modified audio signal at the speaker.
9. The method of claim 1 , wherein the first receiving and the second receiving are performed in parallel.
10. A media device, comprising:
a memory; and
a processor coupled to the memory and configured to:
first receive a voice input at a first voice adapter;
calculate, using the first voice adapter, a first confidence score that the voice input contains a first trigger word, wherein the first trigger word is mapped to a first digital assistant among a plurality of digital assistants stored in a voice platform;
second receive the voice input at a second voice adapter;
calculate, using the second voice adapter, a second confidence score that the voice input contains a second trigger word, wherein the second trigger word is mapped to a second digital assistant, and the second trigger word is different from the first trigger word;
determine the first confidence score is higher than the second confidence score; and
in response to the determination, transmit a request to the voice platform to select the first digital assistant from among the plurality of digital assistants stored in the voice platform.
11. The media device of claim 10 , wherein the processor is further configured to:
normalize, using the first voice adapter, the first confidence score based on a first confidence score criteria.
12. The media device of claim 10 , wherein the processor is further configured to:
determine the first confidence score exceeds a threshold value.
13. The media device of claim 10 , wherein the processor is further configured to:
determine that the first voice adapter generated the first confidence score within a timeout period.
14. The media device of claim 10 , wherein the processor is further configured to:
determine the first confidence score and the second confidence score are within an error range; and
determine the first confidence score is higher than the second confidence score based on a priority criteria.
15. The media device of claim 10 , wherein to first receive the voice input at the first voice adapter the processor is further configured to:
third receive the voice input from an audio responsive electronic device, wherein the audio responsive electronic device is configured to:
output a tone at a speaker;
determine an echo cancellation delay based on a time of receipt of the tone at a microphone; and
perform echo cancellation on the voice input based on the echo cancellation delay.
16. The media device of claim 10 , wherein to first receive the voice input at the first voice adapter the processor is further configured to:
third receive the voice input from an audio responsive electronic device, wherein the audio responsive electronic device is configured to:
generate a first audio signal based on a tone and a second audio signal, wherein the generating distributes the tone across the second audio signal;
output the first audio signal at a speaker;
determine an echo cancellation delay based on a time of receipt of the tone in the first audio signal at a microphone; and
perform echo cancellation on the voice input based on the echo cancellation delay.
17. 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:
first receiving a voice input at a first voice adapter;
calculating, using the first voice adapter, a first confidence score that the voice input contains a first trigger word, wherein the first trigger word is mapped to a first digital assistant among a plurality of digital assistants stored in a voice platform;
second receiving the voice input at a second voice adapter;
calculating, using the second voice adapter, a second confidence score that the voice input contains a second trigger word, wherein the second trigger word is mapped to a second digital assistant, and the second trigger word is different from the first trigger word;
determining the first confidence score is higher than the second confidence score; and
in response to the determining, transmitting a request to the voice platform to select the first digital assistant from among the plurality of digital assistants stored in the voice platform.
18. The non-transitory computer readable medium of claim 17 , the operations further comprising:
normalizing, using the first voice adapter, the first confidence score based on a first confidence score criteria.
19. The non-transitory computer readable medium of claim 17 , the operations further comprising:
determining the first confidence score exceeds a threshold value.
20. The non-transitory computer readable medium of claim 17 , the operations further comprising:
determining that the first voice adapter generated the first confidence score within a timeout period.
21. The non-transitory computer readable medium of claim 17 , the operations further comprising:
determining the first confidence score and the second confidence score are within an error range; and
determining the first confidence score is higher than the second confidence score based on a priority criteria.