US 12,334,076 B2
Selective speech-to-text for deaf or severely hearing impaired
Brant Candelore, Poway, CA (US); and Mahyar Nejat, La Jolla, CA (US)
Assigned to SONY GROUP CORPORATION, Tokyo (JP)
Filed by Sony Group Corporation, Tokyo (JP)
Filed on Oct. 18, 2022, as Appl. No. 17/968,318.
Prior Publication US 2024/0127821 A1, Apr. 18, 2024
Int. Cl. G10L 15/00 (2013.01); G10L 15/26 (2006.01)
CPC G10L 15/26 (2013.01) 4 Claims
OG exemplary drawing
 
4. Smart glasses providing selective speech-to-text functionality, the smart glasses comprising:
one or more microphones;
a speech-to-text processing unit;
a display in a line of sight of a user wearing the smart glasses; and
a voice transcription assistant comprising:
one or more processors; and
logic encoded in one or more non-transitory media for execution by the one or more processors and when executed operable to prevent the speech-to-text processing unit from providing text to the display in response to reception of speech by the one or more microphones unless the logic in the voice transcription assistant determines that the received speech is relevant to the user;
wherein the one or more microphones comprise a first microphone, configured to be responsive primarily to sound incident on the smart glasses from a frontal direction, and a second microphone, configured to be receptive primarily to sound incident on the smart glasses from a rear or lateral direction; and
wherein the logic is further operable to prioritize speech-to-text processing and display of received speech determined to be generated by a person in front of the user over received speech determined to be generated by a person behind or lateral to the user.