Voice tone recognition method and system based on random forest

A technology of random forests and recognition methods, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of complex construction of convolutional neural networks, increase in computational complexity, and influence on recognition accuracy, and reduce parameter calculation and operation speed. Fast and ensure the effect of recognition accuracy

Pending Publication Date: 2020-11-10
SHANDONG UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these methods have a large amount of calculation when calculating the spectrogram and MFCC, and the construction of the convolutional neural network and the deep neural network is also very complicated. At the same time, the recognition accuracy is not high, and the number of hidden layers and the number of nodes in the neural network The selection and optimization of other parameters are generally based on experience, and there is no uniform standard
Similarly, when using the SVM model, the selection of the kernel function is a very important issue, but the selection of the more mature kernel function and its parameters is artificial, and the classic SVM algorithm can only perform binary classification. Applying to multi-classification problems such as tone recognition requires the use of multiple binary classification SVMs, which undoubtedly increases the computational complexity
Moreover, when the data to be identified has problems such as noise, imbalance, and missing data, the recognition accuracy of these models will be greatly affected, and the robustness is poor.

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 tone recognition method and system based on random forest
  • Voice tone recognition method and system based on random forest
  • Voice tone recognition method and system based on random forest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] The present embodiment provides the speech tone recognition method based on random forest;

[0035] Speech tone recognition method based on random forest, including:

[0036] S101: Obtain a speech signal to be recognized, and perform preprocessing on the speech signal to be recognized;

[0037] S102: Extracting and selecting feature parameters of the preprocessed speech signal to be recognized;

[0038] S103: Input the extracted feature parameters into the pre-trained random forest model, and output the tone recognition result of the speech signal to be recognized.

[0039] As one or more embodiments, the preprocessing of the speech signal to be recognized includes: sequentially performing sampling, low-pass filtering, framing and voicing determination on the speech signal to be recognized.

[0040] As one or more embodiments, the extraction and selection of feature parameters are performed on the preprocessed speech signal to be recognized; the specific steps include...

Embodiment

[0063] 1. In the preprocessing part, the sampling rate of the voice signal is 16kHz, and the low-pass filtering is performed by a Chebyshev II low-pass filter with a passband frequency of 500Hz. In the short-time frame processing, the frame length is 30ms, and the frame shift is 10ms. The voicing judgment uses a double-threshold method based on short-term zero-crossing rate and short-term energy.

[0064] 2. Integrating the performance of the feature parameters that have been adopted at the present stage in tone recognition, the following three types of feature parameters are selected for optimization: the basic statistics of the fundamental frequency; , 1 / 3 point to 2 / 3 point, 2 / 3 point to the end), each section extracts four parameters related to the fundamental frequency and energy; parameters related to the fundamental frequency change trend. The above three types of characteristic parameters can form a parameter set, and the weight of each parameter in the parameter set i...

Embodiment 2

[0075] The present embodiment provides the speech tone recognition system based on random forest;

[0076] Speech tone recognition system based on random forest, including:

[0077] A preprocessing module, which is configured to: acquire a speech signal to be recognized, and preprocess the speech signal to be recognized;

[0078] A feature extraction module, which is configured to: extract and select feature parameters for the preprocessed speech signal to be recognized;

[0079] The tone recognition module is configured to: input the extracted feature parameters into a pre-trained random forest model, and output the tone recognition result of the speech signal to be recognized.

[0080] It should be noted here that the above-mentioned preprocessing module, feature extraction module, and tone recognition module correspond to steps S101 to S103 in Embodiment 1, and the examples and application scenarios implemented by the above-mentioned modules are the same as those of the co...

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 discloses a voice tone recognition method and system based on a random forest, and the method comprises the steps: obtaining a to-be-recognized voice signal, and carrying out the preprocessing of the to-be-recognized voice signal; extracting and selecting characteristic parameters of the preprocessed voice signal to be recognized; and inputting the extracted feature parameters into apre-trained random forest model, and outputting a tone recognition result of the to-be-recognized voice signal. The random forest has the advantages of being easy to implement, high in operation speed, high in anti-noise capacity and the like, can be well applied to tone recognition, and can reduce the operation complexity of the tone classifier to the minimum while ensuring the recognition accuracy.

Description

technical field [0001] The present application relates to the technical field of speech tone recognition, in particular to a random forest-based speech tone recognition method and system. Background technique [0002] The statements in this section merely mention the background art related to this application, and do not necessarily constitute the prior art. [0003] Chinese is a tonal language, except for soft tones, there are four tones in Chinese. Tone is reflected in the rise and fall of the sound, which plays an important role in distinguishing meanings in Chinese. Different tones represent different meanings. For example, the pinyin "ma" can be composed of the Chinese characters "Ma", "Ma", "Horse" and "swear" mean. Therefore, as an important part of Chinese, tones play an indispensable role in people's daily communication. At the same time, speech is often used as a communication method in human-computer interaction. Speech recognition is a technology that converts...

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
IPC IPC(8): G10L15/08G10L15/02
CPCG10L15/08G10L15/02
Inventor 田岚李濛刘国洋范辉
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap