Voice identification method and device, computer equipment and storage medium
A speech recognition and computer program technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of time-consuming, labor-intensive, time-consuming, and complicated processing of speech recognition results, saving resources and manpower. Time cost, the effect of improving the accuracy rate
Active Publication Date: 2020-01-14
SHENZHEN RAISOUND TECH
View PDF16 Cites 8 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Because there are no hot words or the probability of hot words is relatively low in the vocabulary of the language model of the basic system, and because the traditional language model is relatively large, it takes a lot of manpower and time to modify the language model in the memory or on the disk , and this change is for a specific task, that is, when undertaking multiple different hot word recognition tasks, it is necessary to process multiple huge language models, which consumes a lot of resources
However, the post-processing method is very complicated to process the speech recognition results, which will also take up a lot of manpower and time costs.
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
[0053] In order to make the purpose, technical solution and advantages of the present application clearer, the present application 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 application, and are not intended to limit the present application.
[0054] The speech recognition method provided by the embodiment of the present invention can be applied to such as figure 1 shown in the application environment. The user terminal 110 is connected to the speech recognition device 120 through a network, and the user terminal 110 includes but is not limited to any one of a mobile phone, a handheld game console, a tablet computer, a personal digital assistant, or a wearable device. The voice recognition device 120 may be any one of a voice recognizer, a server, or a personal computer. The user terminal 110 sends the voice s...
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 relates to a voice identification method and system, computer equipment and a storage medium. The method comprises the steps of acquiring a voice signal, and extracting voice features from the voice signal; carrying out identification on the voice features by a first language model to obtain a first identification result, wherein the first identification result comprises to-be-replaced words; carrying out identification on the voice features by a second language model to obtain a second identification result, wherein the second identification result comprises hot words; identifying a corresponding relationship between the hot words and the to-be-replaced words; and according to the corresponding relationship, replacing the to-be-replaced words with the corresponding hot words. By adopting the method, improvement of accuracy of identifying the hot words can be implemented, so that effective voice identification for the hot words is implemented.
Description
technical field [0001] The invention relates to the technical field of speech processing, in particular to a speech recognition method, device, computer equipment and storage medium. Background technique [0002] Speech recognition technology, also known as automatic speech recognition, aims to convert the content of speech into computer-readable input, such as keystrokes, binary codes, or character sequences, and perform corresponding operations. In the traditional way, the speech recognition model is firstly based on the Hidden Markov Model, among which the Hidden Markov Model with continuous distribution is commonly used. At present, the mainstream of speech recognition has turned to the framework based on WFST (weighted finite state transformer) combined with deep neural network. [0003] At present, there are certain errors in the results of speech recognition, and the error rate of hot words is particularly high. Because there are no hot words or the probability of h...
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): G10L15/22G10L15/06G10L25/24
CPCG10L15/22G10L15/06G10L25/24
Inventor 黄石磊刘轶程刚王昕张涛
Owner SHENZHEN RAISOUND TECH