Continuous reading detection method and device, equipment and storage medium
A technology of continuous reading and grammar, applied in speech analysis, instruments, etc., can solve problems such as difficult continuous reading and distinction, and achieve the effect of high accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0045] figure 1 It is a flow chart of a continuous reading detection method provided by Embodiment 1 of the present disclosure. The method can be executed by a voice detection device, and the voice detection device can be implemented by software and / or hardware. Such as figure 1 As shown, the method specifically includes step S110, step S120 and step S130.
[0046] S110. Obtain the English speech to be evaluated.
[0047] S120. Input the English speech into a logic extension graph for recognition, and the logic extension graph includes a first pronunciation path inserted into a silence model and a second pronunciation path without a silence model inserted.
[0048] Optionally, before step S120, a step of generating a logical extension diagram is also included. Specifically, it may include: obtaining the reference text of the English voice, the reference text includes a mark indicating continuous reading; extracting the mark in the reference text to obtain the normal text, a...
Embodiment 2
[0066] This embodiment provides a device for detecting continuous reading, which can implement the method for detecting continuous reading in the above embodiments, and can be configured in a voice detection device. see image 3 , a detection device for continuous reading, comprising: an acquisition unit 310 , an identification unit 320 and a detection unit 330 . in,
[0067] The acquisition unit 310 is configured to acquire the English voice to be evaluated;
[0068] The recognition unit 320 is configured to input the English speech into a logic extension graph for recognition, and the logic extension graph includes a first pronunciation path inserted into a silence model and a second pronunciation path without a silence model inserted;
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


