公开(公告)号：US20210064920A1

公开(公告)日：2021-03-04

申请号：US17004733

申请日：2020-08-27

Applicant: HYPERCONNECT, INC.

Inventor： Sang Il Ahn ,  Sung Joo Ha ,  Dong Young Kim ,  Beom Su Kim ,  Martin Kersner

IPC: G06K9/62 ,  G06N3/08

Abstract: A method of performing a convolutional operation in a convolutional neural network includes: obtaining input activation data quantized with a first bit from an input image; obtaining weight data quantized with a second bit representing a value of a parameter learned through the convolutional neural network; binarizing each of the input activation data and the weight data to obtain a binarization input activation vector and a binarization weight vector; performing an inner operation of the input activation data and weight data based on a binary operation with respect to the binarization input activation vector and the binarization weight vector and distance vectors having the same length as each of the first bit and the second bit, respectively; and storing a result obtained by the inner operation as output activation data.

公开(公告)号：US11443134B2

公开(公告)日：2022-09-13

申请号：US17004733

申请日：2020-08-27

Applicant: Hyperconnect Inc.

Inventor： Sang Il Ahn ,  Sung Joo Ha ,  Dong Young Kim ,  Beom Su Kim ,  Martin Kersner

IPC: G06K9/62 ,  G06N3/08

Abstract: A method of performing a convolutional operation in a convolutional neural network includes: obtaining input activation data quantized with a first bit from an input image; obtaining weight data quantized with a second bit representing a value of a parameter learned through the convolutional neural network; binarizing each of the input activation data and the weight data to obtain a binarization input activation vector and a binarization weight vector; performing an inner operation of the input activation data and weight data based on a binary operation with respect to the binarization input activation vector and the binarization weight vector and distance vectors having the same length as each of the first bit and the second bit, respectively; and storing a result obtained by the inner operation as output activation data.

公开(公告)号：US20220199068A1

公开(公告)日：2022-06-23

申请号：US17455211

申请日：2021-11-16

Applicant: Hyperconnect, Inc.

Inventor： Sang Il Ahn ,  Seung Woo Choi ,  Seung Ju Han ,  Dong Young Kim ,  Sung Joo Ha

IPC: G10L13/047 ,  G10L15/16 ,  G06N3/04

Abstract: Disclosed is a speech synthesis method including acquiring second speech data and a target text, acquiring first information includes embedding information corresponding to the second speech data, acquiring second information including embedding information of the second speech data, the embedding information in relation with components generated based on a sequence of the target text, and acquiring audio data corresponding to the target text and reflecting characteristics of speech of a speaker based on the first information and the second information.