公开(公告)号：WO2023060054A1

公开(公告)日：2023-04-13

申请号：PCT/US2022/077496

申请日：2022-10-04

Applicant: QUALCOMM INCORPORATED

Inventor： KIM, Byeonggeun ,  YANG, Seunghan ,  PARK, Hyunsin ,  LEE, Juntae ,  CHANG, Simyung

IPC: G10L25/30 ,  G10L25/51 ,  G06N3/045 ,  G06N3/08 ,  G10L17/04 ,  G10L17/18 ,  G10L21/034

Abstract: Techniques and apparatus for training a neural network to classify audio into one of a plurality of categories and using such a trained neural network. An example method generally includes receiving a data set including a plurality of audio samples. A relaxed feature-normalized data set is generated by normalizing each audio sample of the plurality of audio samples. A neural network is trained to classify audio into one of a plurality of categories based on the relaxed feature-normalized data set, and the trained neural network is deployed.

公开(公告)号：WO2022087303A1

公开(公告)日：2022-04-28

申请号：PCT/US2021/056098

申请日：2021-10-21

Applicant: QUALCOMM INCORPORATED

Inventor： CHANG, Simyung ,  PARK, Hyunsin ,  PARK, Hyoungwoo ,  CHO, Janghoon ,  YUN, Sungrack ,  HWANG, Kyu Woong

IPC: G10L15/08 ,  G10L15/16 ,  G10L15/02 ,  G10L25/51 ,  G10L25/30 ,  G10L25/18

Abstract: A computer-implemented method of operating an artificial neural network for processing data having a frequency dimension includes receiving an input. The audio input may be separated into one or more subgroups along the frequency dimension. A normalization may be performed on each subgroup. The normalization for a first subgroup the normalization is performed independently of the normalization a second subgroups. An output such as a keyword detection indication, is generated based on the normalized subgroups.

公开(公告)号：WO2022256802A1

公开(公告)日：2022-12-08

申请号：PCT/US2022/072673

申请日：2022-06-01

Applicant: QUALCOMM INCORPORATED

Inventor： PARK, Hyunsin ,  HOSSEINI, Hossein ,  YUN, Sungrack ,  HWANG, Kyu Woong

IPC: G06N3/08 ,  G06F21/62 ,  H04L9/00

Abstract: Certain aspects of the present disclosure provide techniques for training a machine learning model. The method generally includes receiving, at a local device from a server, information defining a global version of a machine learning model. A local version of the machine learning model and a local center associated with the local version of the machine learning model are generated based on embeddings generated from local data at a client device and the global version of the machine learning model. A secure center different from the local center is generated based, at least in part, on information about secure centers shared by a plurality of other devices participating in a federated learning scheme. Information about the local version of the machine learning model and information about the secure center is transmitted by the local device to the server.

公开(公告)号：WO2022087242A1

公开(公告)日：2022-04-28

申请号：PCT/US2021/056015

申请日：2021-10-21

Applicant: QUALCOMM INCORPORATED

Inventor： CHANG, Simyung ,  KIM, Jangho ,  PARK, Hyunsin ,  LEE, Juntae ,  CHOI, Jaewon ,  HWANG, Kyu Woong

IPC: G06N3/04 ,  G06N3/08

Abstract: A method for generating a personalized model includes receiving one or more personal data samples from a user. A prototype of a personal identity is generated based on the personal data samples. The prototype of the personal identity is trained to reflect personal characteristics of the user. A network graph is generated based on the prototype of the personal identity. One or more channels of a global network are pruned based on the network graph to produce the personalized model.