Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Speech Annotation Method for Chinese Speech Emotion Database Combined with Electroglottogram

An electroglottic map and voice annotation technology, applied in speech analysis, instruments, etc., can solve the problems of lack of unified standards for emotional speech database and complex emotions, so as to achieve comprehensive and detailed annotation information, comprehensive annotation information, and avoid noise interference. Effect

Inactive Publication Date: 2018-01-12
BEIHANG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In recent years, researchers at home and abroad have established multiple speech emotion databases based on their own scientific research tasks. However, due to the complexity of emotions, there is still no unified standard for the establishment and labeling of emotional speech databases. The database is of great significance to the research of speech emotion recognition and speech synthesis.

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
  • A Speech Annotation Method for Chinese Speech Emotion Database Combined with Electroglottogram
  • A Speech Annotation Method for Chinese Speech Emotion Database Combined with Electroglottogram
  • A Speech Annotation Method for Chinese Speech Emotion Database Combined with Electroglottogram

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0024] The present invention proposes a voice labeling method of a Chinese speech emotion database combined with electroglottograms. On the basis of collecting voice signals, the electroglottogram signals are collected at the same time. The electroglottogram directly reflects the vibration information of the vocal cords, avoiding Noise interference during channel modulation and sound propagation, thereby improving the accuracy of speech annotation. The main labeling content of this voice labeling method includes marking eight layers of information for each voice at the same time, which are: the first layer, the text conversion layer, to clarify the speaker's speech content and the corresponding paralinguistic information; the second layer, the syllable layer, labeling The regular pinyin and tone of each syllable; the third layer, the consonant...

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 provides a voice labeling method of a Chinese voice emotion database combined with an electroglottogram. The main marking content of this voice marking method includes marking eight layers of information for each voice at the same time: the first layer, the text conversion layer, clearly defines the speaker's speech content and the corresponding paralinguistic information; the second layer, the syllable layer, marks each syllable The regular pinyin and tone; the third layer, the layer of consonants and finals, marks the consonants and finals of the syllable layer separately, and at the same time marks the tone information; the fourth layer, the layer of unvoiced and voiced sounds and mutes, combined with the electroglottogram to carry out voiceless and muted sounds Segmentation; the fifth layer, the paralinguistic information layer, marks the paralinguistic information contained in each voice; the sixth layer, the emotional layer, according to the emotional state expressed by the speaker, each voice is marked with seven kinds of emotional information and marked with each The degree of expression of each emotion; the seventh layer, the stress index layer, marks the strength information of each syllable pronunciation; the eighth layer, the sentence function layer, marks the sentence type of each sentence.

Description

technical field [0001] The invention relates to a method for voice labeling of a Chinese speech emotion database combined with an electroglottogram. The voice label information is more comprehensive and detailed. The electroglottogram is used to directly reflect the vibration information of the vocal cords, thereby reducing noise interference and improving the accuracy of voice labeling. . Background technique [0002] Speech is one of the most direct ways for people to communicate and express their emotions. With the continuous development of human-computer interaction and affective computing, recognizing the emotional information to be expressed from speech has attracted more and more attention from scholars at home and abroad. Corpus is the basis of speech emotion recognition, so it is extremely important to choose a suitable corpus as the basis of speech emotion analysis and recognition. Segmenting and labeling continuous speech plays an important role in making full u...

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 Patents(China)
IPC IPC(8): G10L21/0208G10L25/63G10L25/93
Inventor 陈立江张娜娜毛峡郑嘉雷景少玲
Owner BEIHANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products