Electronic device and method for speech recognition processing of electronic device

Patent metadata

Field	Value
Publication number	US-11756575-B2
Application number	US-202217677149-A
Country	US
Kind code	B2
Filing date	Feb 22, 2022
Priority date	Feb 16, 2021
Publication date	Sep 12, 2023
Grant date	Sep 12, 2023

Abstract

An electronic device and method are disclosed. The device includes a memory and speech recognition circuitry and/or a processor, which implements the method, including: receiving a first utterance, and processing the first utterance to initiate a session and generate a first response result, after the session related to the first utterance is terminated, receiving a second utterance, processing the second utterance to generate a second response result, based on the second response result, determining whether to execute follow-up utterance processing on the second utterance as if the session were active, based on determining to execute the follow-up utterance processing, reprocessing the second utterance based at least in part on the first response result related to the first utterance to generate a third response result, and outputting the third response result.

First claim

The invention claimed is:

1. A device for supporting a speech recognition service, the device comprising:
a memory; and
speech recognition circuitry operatively connected to the memory, wherein the speech recognition circuitry is configured to:
receive a first utterance, and process the first utterance to initiate a session and generate a first response result;
after the session related to the first utterance is terminated, receive a second utterance;
process the second utterance to generate a second response result;
based on the second response result, determine whether to execute follow-up utterance processing on the second utterance;
based on determining to execute the follow-up utterance processing, reprocess the second utterance based at least in part on the first response result related to the first utterance to generate a third response result; and
output the third response result.

2. The device of claim 1 , wherein processing the first utterance includes initiating the session,
wherein the first utterance is processed according to a first capsule in the session, and
wherein the speech recognition circuitry is further configured to:
after processing the first utterance according to the first capsule, output the generated first response result using a predesignated scheme, and terminate the session based on detecting a termination condition related to the session of the first utterance.

3. The device of claim 2 , wherein the speech recognition circuitry is further configured to:
map a capsule for processing the second utterance, and
process the second utterance based at least in part on the mapped capsule.

4. The device of claim 3 , wherein the speech recognition circuitry is further configured to:
determine whether a history related to the first utterance is extant upon generating the second response result, and
based on detecting that the history is extant, analyze the second response result to determine whether to execute the follow-up utterance processing on the second utterance.

5. The device of claim 4 , wherein determining whether to execute the follow-up processing is further based on a termination time of the session.

6. The device of claim 3 , wherein the speech recognition circuitry is configured to determine to execute the follow-up processing based on at least one of:
detecting a first situation including a recognition failure pertaining to processing of the second utterance, or
detecting a second situation in which the second utterance is processed in a second capsule different from the first capsule in which the first utterance is processed.

7. The device of claim 6 , wherein the speech recognition circuitry is configured to:
based on determining to execute follow-up utterance processing for the second utterance, acquire a capsule identifier of the first capsule in which the first utterance is processed,
wherein mapping the capsule for processing the second utterance includes designating the first capsule corresponding to the acquired capsule identifier for reprocessing of the second utterance.

8. The device of claim 6 , wherein:
when the first situation is detected, the third response result is generated via the follow-up utterance processing on the second utterance, and
when the second situation is detected, the second response result is generated via root utterance processing on the second utterance, and the third response result is generated via follow-up utterance processing on the second utterance.

9. An electronic device, comprising:
communication circuitry;
a display;
a microphone;
a memory; and
at least one processor, configured to:
receive a first utterance via the microphone, and process the first utterance to initial a session and generate a first response result;
after terminating the session related to the first utterance, receive a second utterance via the microphone;
process the second utterance to generate a second response result;
based on the second response result, determine whether to execute follow-up utterance processing on the second utterance;
based on determine to execute the follow-up utterance processing, reprocess the second utterance based at least in part on the first response result related to the first utterance to generate a third response result; and
output the third response result.

10. The electronic device of claim 9 , wherein the at least one processor is further configured to:
determine whether a history related to the first utterance is extant upon generating the second response result, and
based on detecting that the history is extant, analyze the second response result to determine whether to execute the follow-up utterance processing on the second utterance.

11. The electronic device of claim 10 , wherein determining whether to execute the follow-up processing is further based on a termination time of the session.

12. The electronic device of claim 9 , wherein the first utterance is processed according to a first capsule in the session,
wherein the at least one processor is further configured to determine to execute the follow-up processing based on at least one of:
detecting a first situation including a recognition failure pertaining to processing of the second utterance, or
detecting a second situation in which the second utterance is processed in a second capsule different from the first capsule in which the first utterance is processed.

13. The electronic device of claim 12 , wherein the at least one processor is configured to:
based on determining to execute follow-up utterance processing for the second utterance, acquire a capsule identifier of the first capsule in which the first utterance is processed,
wherein mapping the capsule for processing the second utterance includes designating the first capsule corresponding to the acquired capsule identifier for reprocessing of the second utterance.

14. The electronic device of claim 12 , wherein:
when the first situation is detected, the third response result is generated via the follow-up utterance processing on the second utterance, and
when the second situation is detected, the second response result is generated via root utterance processing on the second utterance, and the third response result is generated via follow-up utterance processing on the second utterance.

15. An operation method of an electronic device, the method comprising:
receiving via a microphone a first utterance, and processing via at least one processor the first utterance to initiate a session and generate a first response result;
after the session related to the first utterance is terminated, receiving a second utterance via the microphone;
processing the second utterance to generate a second response result;
based on the second response result, determining whether to execute follow-up utterance processing on the second utterance;
based on determining to execute the follow-up utterance processing, reprocessing the second utterance based at least in part on the first response result related to the first utterance to generate a third response result; and
outputting via output circuitry the third response result.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Son Jisu
• Kim Youngbin
• Cho Jungkeun

Classifications

• G06F40/30 Primary

  Semantic analysis · CPC title

• G10L25/78 Primary

  Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10) · CPC title

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L15/1822

  Parsing for meaning understanding · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title