Invention Grant
- Patent Title: Unsupervised non-parallel speech domain adaptation using a multi-discriminator adversarial network
-
Application No.: US16027111Application Date: 2018-07-03
-
Publication No.: US10783875B2Publication Date: 2020-09-22
- Inventor: Ehsan Hosseini-Asl , Caiming Xiong , Yingbo Zhou , Richard Socher
- Applicant: salesforce.com, inc.
- Applicant Address: US CA San Francisco
- Assignee: salesforce.com, inc.
- Current Assignee: salesforce.com, inc.
- Current Assignee Address: US CA San Francisco
- Agency: Haynes and Boone, LLP
- Main IPC: G10L15/07
- IPC: G10L15/07 ; G10L15/22 ; G10L15/16 ; G06N3/08

Abstract:
A system for domain adaptation includes a domain adaptation model configured to adapt a representation of a signal in a first domain to a second domain to generate an adapted presentation and a plurality of discriminators corresponding to a plurality of bands of values of a domain variable. Each of the plurality of discriminators is configured to discriminate between the adapted representation and representations of one or more other signals in the second domain.
Public/Granted literature
- US20190295530A1 UNSUPERVISED NON-PARALLEL SPEECH DOMAIN ADAPTATION USING A MULTI-DISCRIMINATOR ADVERSARIAL NETWORK Public/Granted day:2019-09-26
Information query