专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

AU2021103917A4 A SYSTEM AND METHOD OF CLASSIFICATION FOR SPEECH REORGANIZATION BASED ON RECURRENT NEURAL NETWORK. 未知
公开(公告)号：AU2021103917A4
公开(公告)日：2021-09-09
申请号：AU2021103917
申请日：2021-07-07
申请人： BHATT VINOD DR , CHOUREY MEENA DR , GUPTA SONENDRA KUMAR DR , KUSHWAH SAPNA SINGH MS , VERMA SHIVALI DR
发明人： VERMA SHIVALI , GUPTA SONENDRA KUMAR , CHOUREY MEENA , KUSHWAH SAPNA SINGH , BHATT VINOD
IPC分类号： G10L15/16
摘要： TITLE OF THE INVENTION "A SYSTEM AND METHOD OF CLASSIFICATION FOR SPEECH REORGANIZATION BASED ON RECURRENT NEURAL NETWORK." The system and method of classification for speech reorganization based on recurrent neural network comprising to the system and classification of the speech reorganization based on the recurrent neural network. More particularly present invention relates to the speech transcriptions, and a few embodiments relate to classifying speech into a number of classifications and a first absolutely-connected community, a recurrent network, a second fully-connected community, and an output community. Also convolutional neural community, the primary absolutely-related neural network, the recurrent neural community, the second one fully-connected neural network, and the output neural network were at the same time trained in an stop-to-give up schooling method to decide their respective educated node weights and one or more laptop-readable media coupled to one or extra of the processing unit(s), the one or greater pc-readable media having thereon one or more modules of executable instructions to configure operations of stop-to-cease recurrent neural community (RNN) version. Page 1 of 1 TITLE OF THE INVENTION "A SYSTEM AND METHOD OF CLASSIFICATION FOR SPEECH REORGANIZATION BASED ON RECURRENT NEURAL NETWORK." Applicant's Name: - Dr Shivali Verma ; Dr Sonendra Kumar Gupta; Dr Meena Chourey; Ms Sapna Singh Kushwah; Dr. Vinod Bhatt. Sheet 1 of 2 Front-end Module Convolutional Neural Network Stack First Fully-Connected Layer ERecurrent Neural Network Stack Second Fully-Connected Layer Output Neural Network Stack Customization Layer Figure 1 Page 1 of 2

IPRDB

热门服务

关于我们

友情链接

联系方式