Invention Grant
- Patent Title: Energy efficient custom deep learning circuits for always-on embedded applications
-
Application No.: US17275484Application Date: 2019-09-13
-
Publication No.: US12014732B2Publication Date: 2024-06-18
- Inventor: Mouna Elkhatib , Adil Benyassine
- Applicant: AONDEVICES, INC.
- Applicant Address: US CA Irvine
- Assignee: AONDEVICES, INC.
- Current Assignee: AONDEVICES, INC.
- Current Assignee Address: US CA Irvine
- Agency: Stetina Brunda Garred & Brucker
- International Application: PCT/US2019/051117 2019.09.13
- International Announcement: WO2020/056329A 2020.03.19
- Date entered country: 2021-03-11
- Main IPC: G10L15/22
- IPC: G10L15/22 ; G06N3/02 ; G06N3/063 ; G10L15/08 ; G10L15/16 ; G10L15/30 ; G10L25/30 ; G10L25/78 ; H03M1/12

Abstract:
A system can include a circuit holistically customized for the detection of commands in an audio or video input signal to meet certain application-specific requirements. The circuit can have a neural network topology that is hardwired to perform detection based on application-specific detection criteria. The hardwired custom circuit can provide improved energy efficiencies compared to similar functionality carried out using software and generic hardware modules. The system can also include a sound change trigger module and perform non-voiced sound detection.
Public/Granted literature
- US20220122592A1 ENERGY EFFICIENT CUSTOM DEEP LEARNING CIRCUITS FOR ALWAYS-ON EMBEDDED APPLICATIONS Public/Granted day:2022-04-21
Information query