US 11,657,814 B2
Techniques for dynamic auditory phrase completion
Stefan Marti, Oakland, CA (US); Joseph Verbeke, San Francisco, CA (US); Evgeny Burmistrov, Saratoga, CA (US); and Priya Seshadri, San Francisco, CA (US)
Assigned to Harman International Industries, Incorporated, Stamford, CT (US)
Filed by HARMAN INTERNATIONAL INDUSTRIES, INCORPORATED, Stamford, CT (US)
Filed on Oct. 8, 2020, as Appl. No. 17/66,433.
Prior Publication US 2022/0115010 A1, Apr. 14, 2022
Int. Cl. G06F 21/32 (2013.01); G10L 15/22 (2006.01); G10L 15/18 (2013.01); G10L 15/183 (2013.01); G10L 15/02 (2006.01)
CPC G10L 15/22 (2013.01) [G10L 15/02 (2013.01); G10L 15/183 (2013.01); G10L 15/1822 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
utilizing an imaging device to capture image data of a user, or an input device to receive a physical input of the user, or a biometric sensor to obtain a biometric value of the user, wherein the image data includes a physical gesture of the user detected by the imaging device, and wherein the physical input includes a triggering input detected by the input device;
utilizing an audio capturing device to acquire a first auditory signal of the user and a processor to detect an initial phrase portion in the first auditory signal; and
using the processor to detect a request from the user to complete a phrase, wherein of the request includes (i) the physical gesture of the user, (ii) the triggering input of the user, or (iii) comparing the biometric value of the user to a threshold, wherein, in response to the request from the user to complete the phrase, the processor is configured to:
retrieve from a database a complete phrase that includes the initial phrase portion;
retrieve a supplemental phrase portion from the complete phrase that complements the initial phrase portion, the initial phrase portion and the supplemental phrase portion forming the complete phrase; and
utilize an audio output device to output an audio reproduction of the supplemental phrase portion.