A speech emotion classification method based on feature fusion and ensemble learning
An integrated learning and emotion classification technology, applied in the field of deep learning, can solve the problems of inability to distinguish typical samples, uneven classification performance, and low recognition accuracy, so as to improve accuracy and stability, enhance representational power, and good representation effect of ability
Active Publication Date: 2022-07-01
上海企创信息科技有限公司
View PDF12 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The focus of this method lies in the construction of the model. However, there are many classification algorithms based on deep learning, and the classification performance is also uneven. A single classification method cannot distinguish typical samples, and the generally extracted spectrogram is a spectrogram or Mel spectrum. Figure, relatively single, the overall recognition accuracy is low
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
[0064] The specific embodiments of the present invention are described below to facilitate those skilled in the art to understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, as long as various changes Such changes are obvious within the spirit and scope of the present invention as defined and determined by the appended claims, and all inventions and creations utilizing the inventive concept are within the scope of protection.
[0065] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
[0066] like figure 1 As shown, a speech emotion classification method based on feature fusion and ensemble learning solves the problems existing in the prior art.
[0067] In order to achieve the above purpose of the invention, the technical solution adopted in the present invention is: a speech emotion classifi...
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 voice emotion classification method based on feature fusion and integrated learning, comprising the following steps: collecting a number of voice data, and preprocessing the voice data; extracting features from the preprocessed data, and constructing a feature set; Multi-classifiers are used to build an ensemble learning classification model, and the ensemble learning classification model is trained; the trained ensemble learning classification model is used to identify the corresponding feature set of the speech data to be recognized, and the classification results are obtained, and the speech emotion classification results are obtained. The present invention can effectively predict and classify the speaker's speech emotion through speech data.
Description
technical field [0001] The invention belongs to the field of deep learning, and in particular relates to a speech emotion classification method based on feature fusion and integrated learning. Background technique [0002] With the rapid development of computer technology, computers have become an indispensable part of people's lives. The current field of human-computer interaction is no longer limited to keyboards and screens, but has expanded to voice interaction, such as Baidu's "Xiaodu", Microsoft's "Xiaobing", and Apple's "Siri". However, the existing voice interaction is relatively "cold", lacking "emotion", and the user experience is not good. Mining emotional information from the speaker's speech data is a popular research direction in the field of speech signals in recent years. It is of great significance to improve the level of human-computer interaction and has very important research and application value. [0003] At present, the technical solutions and techn...
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 Patents(China)
IPC IPC(8): G06K9/62G06N20/20G10L25/63
CPCG10L25/63G06F18/2115G06F18/2148G06F18/2411G06F18/24147G06F18/2415G06F18/24323G06F18/24G06F18/253
Inventor 郭奕熊雪军徐亮黄永茂卿朝进黄文韬
Owner 上海企创信息科技有限公司