US 11,929,087 B2
Systems and methods for selectively attenuating a voice
Tal Rosenwein, Jerusalem (IL); Roi Nathan, Jerusalem (IL); Ronen Katsir, Erfat (IL); Yonatan Wexler, Jerusalem (IL); and Amnon Shashua, Mevaseret Zion (IL)
Assigned to ORCAM TECHNOLOGIES LTD., Jerusalem (IL)
Filed by OrCam Technologies Ltd., Jerusalem (IL)
Filed on Sep. 16, 2021, as Appl. No. 17/447,851.
Claims priority of provisional application 63/087,350, filed on Oct. 5, 2020.
Claims priority of provisional application 63/079,502, filed on Sep. 17, 2020.
Prior Publication US 2022/0084537 A1, Mar. 17, 2022
Int. Cl. G10L 21/0316 (2013.01); G10L 15/24 (2013.01); G10L 21/003 (2013.01); G10L 25/78 (2013.01)
CPC G10L 21/0316 (2013.01) [G10L 15/24 (2013.01); G10L 21/003 (2013.01); G10L 25/78 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A system for selectively amplifying audio signals, the system comprising:
at least one microphone configured to capture sounds from an environment of the user; and
at least one processor programmed to:
receive an audio signal representative of sounds captured by the at least one microphone;
determine a first part of the audio signal that comprises speech by a user of the system;
determine a second part of the audio signal that comprises audio other than the speech by the user;
attenuate the first part of the audio signal comprising the speech by the user by decreasing at least one of an amplitude, sound level, or power level of the first part of the audio signal;
amplify the second part of the audio signal comprising audio other than the speech by the user by increasing at least one of an amplitude, sound level, or power level of the second part of the audio signal;
perform additional processing on the amplified second part of the audio signal without attenuating the amplified second part of the audio signal to generate an additionally modified second part of the audio signal, wherein the additional processing comprises at least one of enhancing diction, modifying a pitch, reducing a playback speed, or changing a gap between words; and
transmit, to a hearing interface device, the attenuated first part of the audio signal without performing the additional processing on the attenuated first part of the audio signal and the additionally modified second part of the audio signal.