Wake word selection assistance architectures and methods

Patent metadata

Field	Value
Publication number	US-11222622-B2
Application number	US-201916522427-A
Country	US
Kind code	B2
Filing date	Jul 25, 2019
Priority date	May 5, 2019
Publication date	Jan 11, 2022
Grant date	Jan 11, 2022

Abstract

Generally discussed herein are devices, systems, and methods for custom wake word selection assistance. A method can include receiving, at a device, data indicating a custom wake word provided by a user, determining one or more characteristics of the custom wake word, determining that use of the custom wake word will cause more than a threshold rate of false detections based on the characteristics, rejecting the custom wake word as the wake word for accessing a personal assistant in response to determining that use of the custom wake word will cause more than a threshold rate of false detections, and setting the custom wake word as the wake word in response to determining that use of the custom wake word will not cause more than the threshold rate of false detections.

First claim

What is claimed is:

1. A method for custom wake word selection assistance, the method comprising:
receiving, at a device, data indicating a custom wake word provided by a user;
determining one or more characteristics of the custom wake word including determining a number of phonemes of variable duration in the custom wake word;

and
setting the custom wake word as the wake word in response to determining that the determined number of phonemes of variable duration is less than a threshold number.

2. The method of claim 1 , wherein determining one or more characteristics of the custom wake word further includes determining a number of phonemes in the custom wake word and the method further includes rejecting the custom wake word as the wake word in response to determining the number of phonemes is less than a threshold number of phonemes.

3. The method of claim 1 , wherein determining one or more characteristics of the custom wake word further includes determining a number of words within a specified semantic distance of the custom wake word and the method further includes rejecting the custom wake word as the wake word in response to determining the determined number of words is greater than a specified number of words.

4. The method of claim 1 , wherein determining one or more characteristics of the custom wake word further includes determining whether the custom wake word is a proper subset of another word and the method further includes rejecting the custom wake word as the wake word in response to determining the custom wake word is a proper subset of another word.

5. The method of claim 1 , further comprising:
providing a series of possible pronunciations of the custom wake word;
receiving data indicating which of the possible pronunciations were selected by a user; and
determining the one or more characteristics based on the selected pronunciations.

6. The method of claim 5 , wherein the possible pronunciations are provided in text form or audio form.

7. The method of claim 1 , wherein determining the one or more characteristics of the custom wake word further includes determining, using a speech recognition model, a false acceptance rate based on audio that does not include the custom wake word.

8. The method of claim 1 , wherein determining the one or more characteristics of the custom wake word further includes determining, using a speech recognition model, a correct acceptance rate based on audio that includes the custom wake word.

9. The method of claim 7 , wherein the audio is synthetically generated using various voice fonts, emotions, and prosody.

10. The method of claim 8 , wherein the audio is synthetically generated with utterances of the custom wake word using various voice fonts, emotions, and prosody.

11. The method of claim 1 , wherein determining the one or more characteristics of the custom wake word further includes determining a number of stop sounds and plosives in the custom wake word and rejecting the custom wake word as the wake word in response to determining the number of stop sounds and plosives is less than a threshold number.

12. The method of claim 1 , wherein:
determining the one or more characteristics of the custom wake word further includes determining at least two characteristics,
the method further includes determining a weighted combination of the at least two characteristics, and
rejecting the custom wake word as the wake word in response to determining the weight combination is less than a threshold.

13. A system comprising:
processing circuitry;
memory including instructions that, when executed by the processing circuitry, cause the processing circuitry to perform operations for custom wake word selection, the operations comprising:
determining one or more characteristics of a custom wake word including determining a number of phonemes of variable duration in the custom wake word;
and
setting the custom wake word as the wake word in response to determining that the determined number of phonemes of variable duration is less than a threshold number.

14. The system of claim 13 , wherein determining one or more characteristics of the custom wake word further includes determining a number of phonemes in the custom wake word and the method further includes rejecting the custom wake word as the wake word in response to determining the number of phonemes is less than a threshold number of phonemes.

15. The system of claim 13 , wherein determining one or more characteristics of the custom wake word further includes determining a number of words within a specified semantic distance of the custom wake word and the method further includes rejecting custom wake word as the wake word in response to determining the determined number of words is greater than a specified number of words.

16. The system of claim 13 , wherein determining one or more characteristics of the custom wake word further includes determining whether the custom wake word is a proper subset of another word and the method further includes rejecting the custom wake word as the wake word in response to determining the custom wake word is a proper subset of another word.

17. A non-transitory machine-readable medium including instructions that, when executed by a machine, cause the machine to perform operations of custom wake word selection assistance, the operations comprising:
determining one or more characteristics of a custom wake word including determining a number of phonemes of variable duration in the custom wake word;
and
setting the custom wake word as the wake word in response to determining that the determined number of phonemes of variable duration is less than a threshold number.

18. The non-transitory machine-readable medium of claim 17 , wherein the operations further comprise:
providing a series of possible pronunciations of the custom wake word;
receiving data indicating which of the possible pronunciations were selected by a user; and
determining the one or more characteristics based on the selected pronunciations.

19. The non-transitory machine-readable medium of claim 17 , wherein determining the one or more characteristics of the custom wake word further includes determining, using a speech recognition model, a false acceptance rate based on audio that does not include the custom wake word.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Stoimenov Emilian
• Shahid Khuram
• Ye Guoli
• Khalil Hosam Adel
• Gong Yifan

Classifications

• G10L13/10

  Prosody rules derived from text; Stress or intonation · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/07 Primary

  to the speaker · CPC title

• G10L2015/088

  Word spotting · CPC title

• G06F40/30

  Semantic analysis · CPC title