Speech recognition confidence estimation method and device and computer equipment
A technology of computer equipment and speech recognition, which is applied in the field of confidence estimation of speech recognition, and can solve problems such as unsatisfactory calculation results of confidence
Pending Publication Date: 2022-04-22
普强时代(珠海横琴)信息技术有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The embodiment of the present application solves the problem of unsatisfactory confidence calculation effect in speech recognition in the prior art by providing a speech recognition confidence estimation method, device and computer equipment
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
[0041] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
[0042] The flowcharts shown in the figures are for illustration only, and do not necessarily include all contents and operations / steps, nor do they have to be performed in the order described. For example, some operations / steps can also be decomposed, combined or partially combined, so the actual execution order may be changed according to the actual situation.
[0043] see figure 1 shown, figure 1 It is a schematic diagram of a meth...
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 confidence estimation method, device and equipment for speech recognition. The method comprises the following steps: acquiring a to-be-estimated statement; sending the to-be-estimated statement into the acoustic model for calculation and decoding to obtain a posterior value of the acoustic model state corresponding to each phoneme in the to-be-estimated statement; sending the posterior value of the phoneme into a pre-constructed phoneme fuzzy matrix, and calculating a single-phoneme confidence coefficient; and calculating the confidence coefficient of the to-be-estimated statement according to the single phoneme confidence coefficient. According to the invention, the phoneme fuzzy matrix is utilized to calculate the confidence of the single phoneme so as to obtain the confidence of the whole voice, and the problems that the confidence calculation effect is not ideal, the calculation amount is large, the accuracy is influenced and the like in the existing confidence calculation method are solved.
Description
technical field [0001] The present invention relates to the field of artificial intelligence, and in particular, to a method, device and computer equipment for estimating confidence of speech recognition. Background technique [0002] With the continuous development of artificial intelligence and speech recognition technology, and the increasing demand for improving the efficiency of human-computer interaction, higher requirements are placed on the confidence of speech recognition. [0003] Confidence includes accuracy rate and recognition ability. Accuracy rate is to convert the "voice" issued by human speech into the corresponding form of "text". Rejection ability is to recognize and exclude unexpected input such as noise. [0004] Confidence can reflect the reliability of the recognition result. In the existing confidence calculation methods for speech recognition, there are problems such as unsatisfactory calculation of confidence, large amount of calculation, and influe...
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 Applications(China)
IPC IPC(8): G10L15/01G10L15/18G10L15/06
CPCG10L15/01G10L15/18G10L15/063G10L2015/025
Inventor 张钰辉赵茂详李全忠何国涛蒲瑶
Owner 普强时代(珠海横琴)信息技术有限公司