Voice recognition method and system based on incremental word graph re-scoring
A technology of speech recognition and word map, which is applied in speech recognition, speech analysis, instruments, etc., can solve the problems of insufficient recognition speed, large final word map, and difference influence, so as to improve recognition accuracy, realize self-adaptation, Speed up the generated effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0058] First, the methods and terms involved in the present invention will be described.
[0059] 1) Finite state receiver (FSA): Weighted finite state transcription machine (WFST) consists of a set of states and directed jumps between states, in which three kinds of information are saved on each jump, namely input label, output label and weight, recorded in the format of "input_label:output_label / weight", the decoding network mentioned in the present invention is a WFST. FSA can be seen as a simplification of FST, each of its jumps has only input labels.
[0060] 2) State-level word graph: a directed acyclic graph with input labels, output labels, and weight values on transition edges. The input label is the alignment information, and the output label is the word result.
[0061] 3) Word-level word graph: also called compressed word graph, which is obtained by determinizing the state-level word graph. The difference from the state-level word graph is that its alignment in...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com