US 11,922,953 B2
Voice recognition device, control method of voice recognition device, content reproducing device, and content transmission/reception system
Hideo Omura, Kanagawa (JP)
Assigned to Nissan Motor Co., Ltd., Kanagawa (JP); and RENAULT S.A.S., Boulogne-Billancourt (FR)
Appl. No. 17/414,194
Filed by Nissan Motor Co., Ltd., Kanagawa (JP); and RENAULT S.A.S., Boulogne-Billancourt (FR)
PCT Filed Dec. 18, 2018, PCT No. PCT/IB2018/001565
§ 371(c)(1), (2) Date Jun. 15, 2021,
PCT Pub. No. WO2020/128552, PCT Pub. Date Jun. 25, 2020.
Prior Publication US 2022/0044691 A1, Feb. 10, 2022
Int. Cl. G10L 17/26 (2013.01); G10L 25/69 (2013.01); G10L 25/81 (2013.01); G10L 25/84 (2013.01); G10L 15/22 (2006.01); G10L 25/93 (2013.01)
CPC G10L 17/26 (2013.01) [G10L 25/69 (2013.01); G10L 25/81 (2013.01); G10L 25/84 (2013.01); G10L 2015/223 (2013.01); G10L 25/93 (2013.01)] 11 Claims
OG exemplary drawing
 
3. A control method of a voice recognition device by a processor comprising:
detecting whether a content reproducing device including a voice output unit reproduces a content;
analyzing whether a specific characteristic component is included in a voice signal input into a voice input unit when it is detected that the content reproducing device reproduces a content;
recognizing a voice by executing voice recognition processing of the voice represented by the voice signal input into the voice input unit when it is detected that the voice signal does not include the specific characteristic component;
instructing a response to a response operation unit that operates in response to a recognized voice; and
performing control not to execute the voice recognition processing of the voice represented by the voice signal input into the voice input unit or perform control not to instruct the response operation unit about an instruction content by the voice recognized by executing the voice recognition processing, when it is analyzed that the voice signal includes the specific characteristic component,
wherein the specific characteristic component is an artificial waveform component superimposed on the voice signal by a content signal corrector at a predetermined time interval.