Voice recognition and voice synthesis model training method based on dual learning
A speech recognition model and speech synthesis technology, applied in the fields of speech synthesis, speech recognition, speech recognition and speech synthesis, can solve the problems of high cost, time-consuming and laborious, and it is difficult to ensure data quality, so as to save cost and solve data problems. small number of effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0019] The present invention will be further described below in conjunction with specific drawings and embodiments.
[0020] The general idea of the present invention is: first, use less labeled data to pre-train the speech recognition model and the speech synthesis model; then, through the dual learning method, use a large amount of unlabeled data and reinforcement learning technology to avoid In a supervised way, the speech recognition model and speech synthesis model are further trained.
[0021] First, define the input of the algorithm, including: speech data set D used to train speech recognition and speech synthesis models A , Text data set D B ; The voice recognition model to be trained Θ AB ; The speech synthesis model to be trained Θ BA ; Pre-trained speech language model LM used to calculate the confidence that speech data is generated by humans instead of machines A ; Pre-trained text language model LM used to calculate the confidence that the text data is written by...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap