-
公开(公告)号：US20240355320A1
公开(公告)日：2024-10-24
申请号：US18371289
申请日：2023-09-21
CPC分类号： G10L15/063 , G10L15/16 , G10L15/20
摘要： A system including: one or more processors; and memory including instructions that, when executed by the one or more processors, cause the one or more processors to: generate augmented input data by mixing noise components of training data; train a first neural network based on the augmented input data and ground truth data of the training data to output a first prediction of clean speech; lock trainable parameters of the first neural network as a result of the training of the first neural network; and train a second neural network according to the augmented input data and predictions of the first neural network to output a second prediction of the clean speech.
-
2.发明授权公开(公告)号：US12051237B2
公开(公告)日：2024-07-30
申请号：US17674832
申请日：2022-02-17
IPC分类号： G06V10/82 , G06N5/04 , G06V10/774 , G06V10/776 , G06V10/778
CPC分类号： G06V10/82 , G06N5/04 , G06V10/774 , G06V10/776 , G06V10/7784
摘要： A system and a method to train a neural network are disclosed. A first image is weakly and strongly augmented. The first image, the weakly and strongly augmented first images are input into a feature extractor to obtain augmented features. Each weakly augmented first image is input to a corresponding first expert head to determine a supervised loss for each weakly augmented first image. Each strongly augmented first image is input to a corresponding second expert head to determine a diversity loss for each strongly augmented first image. The feature extractor is trained to minimize the supervised loss on weakly augmented first images and to minimize a multi-expert consensus loss on strongly augmented first images. Each first expert head is trained to minimize the supervised loss for each weakly augmented first image, and each second expert head is trained to minimize the diversity loss for each strongly augmented first image.
-
公开(公告)号：US11687780B2
公开(公告)日：2023-06-27
申请号：US17241848
申请日：2021-04-27
IPC分类号： G06K9/62 , G06N3/08 , G06F18/2323 , G06F18/2415 , G06F18/2431 , G06V30/19 , G06V10/772 , G06V10/774 , G06V10/80 , G06F18/2321 , G06F18/25 , G06N3/045 , G06N3/04 , G06N5/022 , G06N5/025
CPC分类号： G06N3/08 , G06F18/2321 , G06F18/2323 , G06F18/2415 , G06F18/2431 , G06F18/253 , G06F18/254 , G06N3/04 , G06N3/045 , G06N5/022 , G06N5/025 , G06V10/772 , G06V10/774 , G06V10/806 , G06V10/809 , G06V30/1914 , G06V30/1918 , G06V30/19107 , G06V30/19147
摘要： A method and system for training a neural network are provided. The method includes receiving an input image, selecting at least one data augmentation method from a pool of data augmentation methods, generating an augmented image by applying the selected at least one data augmentation method to the input image, and generating a mixed image from the input image and the augmented image.
-
-
搜索结果
3 条记录 (耗时 0.017 秒)
