US 11,893,997 B2
Audio signal processing for automatic transcription using ear-wearable device
Achintya Kumar Bhowmik, Cupertino, CA (US); David Alan Fabry, Eden Prairie, MN (US); Amit Shahar, Hod HaSharon (IL); and Clifford Anthony Tallman, Hopkins, MN (US)
Assigned to Starkey Laboratories, Inc., Eden Prairie, MN (US)
Filed by Starkey Laboratories, Inc., Eden Prairie, MN (US)
Filed on Jan. 26, 2022, as Appl. No. 17/585,227.
Application 17/585,227 is a continuation of application No. 16/732,756, filed on Jan. 2, 2020, granted, now 11,264,035.
Claims priority of provisional application 62/788,816, filed on Jan. 5, 2019.
Prior Publication US 2022/0148599 A1, May 12, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 17/00 (2013.01); G06F 3/01 (2006.01); G10L 17/04 (2013.01); H04R 1/10 (2006.01)
CPC G10L 17/00 (2013.01) [G06F 3/012 (2013.01); G10L 17/04 (2013.01); H04R 1/1016 (2013.01); H04R 1/1041 (2013.01)] 23 Claims
OG exemplary drawing
 
1. A method of automatic transcription using a display device and an ear-wearable device configured to be worn by a user in contact with an ear of the user, wherein the ear-wearable device comprises a first control circuit, a first electroacoustic transducer for generating sound in electrical communication with the first control circuit, a first microphone in electrical communication with the first control circuit, a memory storage, and a wireless communication device, wherein the ear-wearable device is configured to direct sound from the first transducer toward the user's ear when the ear-wearable device is worn by the user, the display device comprising a second control circuit and a second wireless communication device, the method comprising:
receiving an input audio signal, the input audio signal comprising a first voice signal originating from a first speaker and a second voice signal originating from a second speaker;
processing the input audio signal to identify the first voice signal and the second voice signal from the input audio signal, wherein the first voice signal comprises characteristics indicating the first speaker as source for the first voice signal and the second voice signal comprises characteristics indicating the second speaker as source for the second voice signal;
displaying on the display device a representation of the first voice signal and the second voice signal;
receiving user input from the user at either the ear-wearable device or the display device selecting one of the first voice signal and the second voice signal as a selected voice signal;
converting the selected voice signal of the first voice signal or second voice signal to text data;
displaying a transcript on the display device, wherein the transcript comprises content spoken in the input audio signal by the selected voice signal of the first voice signal or second voice signal; and
generating an output signal sound at the first transducer of the ear-wearable device based on the input audio signal, whereby the output signal is relayed to the user's ear by the first transducer.