Unlock instant, AI-driven research and patent intelligence for your innovation.

Voice fluency detection method and device

A detection method and fluency technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problem of ignoring influence, etc., and achieve the effect of improving the effect and improving the effect.

Pending Publication Date: 2021-02-23
武汉国平教育科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, it is necessary to provide a method and device for detecting speech fluency to solve the problem that the influence of speech fluency on speech recognition is ignored in current speech recognition systems

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Voice fluency detection method and device
  • Voice fluency detection method and device
  • Voice fluency detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Such as figure 1 As shown, Embodiment 1 of the present invention provides a speech fluency detection method, is characterized in that, comprises the following steps:

[0035] S1. Collect voice sample signals, and put semantic labels on the voice sample signals, and establish a training sample set;

[0036] S2. Using the training sample set to train the neural network to obtain a speech recognition model;

[0037] S3. Collect the speech signal to be tested, and perform preprocessing on the speech signal to be tested;

[0038] S4. Extracting a feature vector of the preprocessed speech signal, and inputting the feature vector into the speech recognition model to obtain corresponding semantic text information;

[0039] S5. Calculate the probability that the semantic text information appears in the corpus, and judge whether the probability is lower than a set threshold, if yes, the speech is not smooth, otherwise the speech is smooth.

[0040] In order to judge whether th...

Embodiment 2

[0068] Embodiment 2 of the present invention provides a speech fluency detection device, including a processor and a memory, and a computer program is stored on the memory. When the computer program is executed by the processor, the speech fluency provided by Embodiment 1 is realized. Detection method.

[0069] The speech fluency detection device provided by the embodiment of the present invention is used to implement the speech fluency detection method. Therefore, the speech fluency detection device also possesses the technical effects of the speech fluency detection method, and will not be repeated here.

Embodiment 3

[0071] Embodiment 3 of the present invention provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the speech fluency detection method provided in Embodiment 1 is implemented.

[0072] The computer storage medium provided by the embodiment of the present invention is used to implement the speech fluency detection method. Therefore, the technical effects of the speech fluency detection method are also provided by the computer storage medium, which will not be repeated here.

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

No PUM Login to View More

Abstract

The invention relates to a voice fluency detection method comprising the following steps: collecting a voice sample signal, marking a semantic tag on the voice sample signal, and establishing a training sample set; training a neural network by adopting the training sample set to obtain a voice recognition model; collecting a to-be-detected voice signal, and preprocessing the to-be-detected voice signal; extracting a feature vector of the preprocessed voice signal, and inputting the feature vector into the voice recognition model to obtain corresponding semantic text information; and calculating the occurrence probability of the semantic text information in a corpus, judging whether the probability is lower than a set threshold value or not, if the probability is lower than a set thresholdvalue, indicating that the voice is not smooth, and otherwise, indicating that the voice is smooth. According to the invention, the fluency is detected while voice recognition is carried out, so thatthe effect of subsequent voice interaction is ensured.

Description

technical field [0001] The invention relates to the technical field of speech fluency detection, in particular to a speech fluency detection method, device and computer storage medium. Background technique [0002] Intelligent voice interaction is a new generation of interaction mode based on voice input, and feedback results can be obtained by speaking. Speech recognition technology is a high technology that allows machines to convert voice signals into corresponding text or commands through the process of recognition and understanding. Speech recognition technology mainly includes three aspects: feature extraction technology, pattern matching criteria and model training technology. [0003] Voice is a kind of wave, and the voice signal is essentially a one-dimensional waveform. The fluency of voice is directly related to the interactive experience. However, in the current voice interaction, it is usually focused on the improvement of pre-processing recognition technology,...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/16G10L21/0208G10L25/24G10L15/26
CPCG10L15/16G10L21/0208G10L25/24G10L15/26
Inventor 涂晓帆夏敏
Owner 武汉国平教育科技有限公司