Method and system for fast speech recognition
A fast speech and speech technology, applied in speech recognition, speech analysis, instruments, etc., to achieve the effect of improving calculation speed, accurate algorithm, and improving the accuracy of verification
Active Publication Date: 2022-04-19
XIAMEN KUAISHANGTONG TECH CORP LTD
View PDF12 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
There are two problems with this method, one is computing resource consumption and computing speed, and the other is its accuracy
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer and clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0033] Such as figure 1 Shown, a kind of fast speech recognition method of the present invention, it comprises the following steps:
[0034] Generate a state network diagram based on a preset text database;
[0035] Obtain the voice to be verified and the text content corresponding to the voice to be verified;
[0036] Extracting a corresponding state path from the state network graph according to the text content, where the nodes of the state path are phonemes;
[0037] The speech to be verified is divided into more than one speech frame, and the ac...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method and system for rapid speech recognition, which comprises the following steps: generating a state network diagram according to a preset text database; obtaining a speech to be verified and the text content corresponding to the speech to be verified; Extract the corresponding state path in the state network graph, the node of the state path is a phoneme; divide the speech to be verified into more than one speech frame, and extract the corresponding acoustic features of the speech frame; The feature is aligned with the state path, and the node corresponding to each speech frame is obtained; the corresponding posterior probability is calculated according to the speech frame and the phoneme of the corresponding node, and the average posterior probability of all speech frames of the speech to be verified is calculated. Posterior probability; Threshold calculation is performed on the average posterior probability to determine whether the speech to be verified matches the text content, thereby reducing computing resource consumption and improving computing speed and verification accuracy.
Description
technical field [0001] The invention relates to the technical field of speech recognition, in particular to a fast speech recognition method and a system for applying the method. Background technique [0002] With the development of pattern recognition and artificial intelligence, speech technology and voiceprint recognition technology have made great progress and began to play an increasingly important role in real life. [0003] Speech recognition refers to the technology of converting speech into text. Through speech recognition, the computer can know the text content dictated by the user. The classification of speech recognition can be divided into large, medium and small scale in terms of vocabulary size; in terms of form, it can be divided into isolated words and continuous speech recognition. Since the development of speech recognition technology in the 1980s to the present, with the accumulation of corpus and the advancement of algorithms, the recognition ability ha...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G10L25/03G10L25/24G10L15/26G10L15/22
CPCG10L25/03G10L25/24G10L15/22G10L15/26
Inventor 洪国强肖龙源李稀敏蔡振华刘晓葳谭玉坤
Owner XIAMEN KUAISHANGTONG TECH CORP LTD