US 12,094,460 B2
Electronic device and voice recognition method thereof
Jae-Hyun Bae, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Appl. No. 16/317,865
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
PCT Filed Jul. 18, 2017, PCT No. PCT/KR2017/007738
§ 371(c)(1), (2) Date Jan. 15, 2019,
PCT Pub. No. WO2018/021750, PCT Pub. Date Feb. 1, 2018.
Claims priority of application No. 10-2016-0095301 (KR), filed on Jul. 27, 2016.
Prior Publication US 2021/0280178 A1, Sep. 9, 2021
Int. Cl. G10L 15/08 (2006.01); G10L 15/22 (2006.01); G10L 15/26 (2006.01); G10L 15/32 (2013.01)
CPC G10L 15/22 (2013.01) [G10L 15/26 (2013.01); G10L 15/32 (2013.01); G10L 2015/088 (2013.01)] 14 Claims
OG exemplary drawing
 
1. An electronic device, comprising:
a display;
a voice input interface configured to receive a user voice input; and
a processor configured to:
receive the user voice input through the voice input interface,
based on a predetermined word input being included in the user voice input according to a first speech recognition operation, identify a part of the user voice input in which the predetermined word input is included, obtain a first text corresponding to a part of the user voice input excluding the predetermined word input included in the identified part, perform a function of a second speech recognition operation corresponding to the obtained first text, and output a first result relating to the part of the user voice input excluding the predetermined word input, and
based on the predetermined word input not being included in the user voice input according to the first speech recognition operation, obtain a second text corresponding to the user voice input, perform the function of the second speech recognition operation corresponding to the obtained second text and output a second result relating to the user voice input,
wherein the part of the user voice input excluding the predetermined word input comprises a first part and a second part,
wherein the predetermined word input is between the first part and the second part,
wherein the predetermined word input includes a voice input which is meaninglessly uttered by a user, and
wherein the first result of performing the function of the speech recognition corresponding to the obtained first text is same as the second result of performing the function of the speech recognition based on the obtained second text.