Electronic device speech recognition method thereof
AssigneeSamsung Electronics Co., Ltd.
InventorChanhee Choi
Life of this patent
Estimating the term…
Abstract
An electronic device includes: a memory storing instructions; and a processor operatively connected to the memory and configured to execute the instructions to: perform a first analysis operation of confirming a recognition error for a voice based on an input time of the voice; determine whether to perform a second analysis operation of confirming the recognition error in response to a result of the first analysis operation; based on a determination to perform the second analysis operation, perform the second analysis operation based on a text corresponding to the voice; and provide a recognition result of the voice based on a result of the second analysis operation.
Claims18
An electronic device comprising:
- at least one processor including processing circuitry,
- memory storing instructions that, when executed by the at least one processor individually or collectively, cause the electronic device to:
- perform a first analysis operation of confirming a recognition error for a voice;
- obtain a first analysis score for the first analysis operation based on a detection of an end point of the voice and a length of a text corresponding to the voice;
- determine whether to perform a second analysis operation of confirming the recognition error by comparing the first analysis score with a first threshold value;
- based on a determination to perform the second analysis operation, perform the second analysis operation based on the text;
- and
- provide a recognition result of the voice based on a result of the second analysis operation.
A method performed by an electronic device, the method comprising:
- performing a first analysis operation of confirming a recognition error for a voice;
- obtaining a first analysis score for the first analysis operation based on a detection of an end point of the voice and a length of a text corresponding to the voice;
- determining whether to perform a second analysis operation of confirming the recognition error by comparing the first analysis score with a first threshold value;
- based on determining to perform the second analysis operation, performing the second analysis operation based on the text;
- and
- providing a recognition result of the voice based on a result of the second analysis operation.
Dependencies are inferred from the claim text.