Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Automatic detection method for uraniscolalia pharyngeal fricatives based on FTSL spectral line

A cleft palate speech and automatic detection technology, applied in speech analysis, instruments, character and pattern recognition, etc., can solve the problems of not realizing the automatic classification and detection of pharyngeal fricatives and normal fricatives, not being objective and accurate enough

Active Publication Date: 2018-11-30
SICHUAN UNIV
View PDF11 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the change of each parameter is still a subjective evaluation, and there are still problems of not being objective and accurate enough.
2) Analysis of time-frequency characteristics of pharyngeal fricatives based on digital signal processing technology. Corresponding studies explored the relationship between energy distribution and pharyngeal fricatives, but did not realize automatic classification and detection of pharyngeal fricatives and normal fricatives

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
  • Automatic detection method for uraniscolalia pharyngeal fricatives based on FTSL spectral line
  • Automatic detection method for uraniscolalia pharyngeal fricatives based on FTSL spectral line
  • Automatic detection method for uraniscolalia pharyngeal fricatives based on FTSL spectral line

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution of the present invention is clearly and completely described below in conjunction with the accompanying drawings of the present invention. Based on the embodiments in this application, those of ordinary skill in the art will Other similar embodiments obtained without creative work shall all fall within the scope of protection of this application.

[0073] It should be noted that the speech data used in this embodiment is obtained by recording according to the Mandarin articulation measurement table, which includes all consonants in the Mandarin syllables, and according to the characteristics of the consonant pronunciation of the pharyngeal fricative, select the consonant / s Words of / , / sh / , / c / , / x / , for example, "shark" in "shark", "west" in "watermelon", etc. The voice data is judged by a professional voice engineer in the early stage, an...

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 an automatic detection method for uraniscolalia pharyngeal fricatives based on a multi-delay four-order-cumulant-octave FTSL spectral line, and relates to the field of voice signal processing. The detection method comprises the following steps: (1) carrying out signal preprocessing, namely, carrying out framing, pre-emphasis and amplitude normalization on input consonant signals; (2) extracting the features of voice signals, namely, extracting FTSL spectral line features in the frequency domain of the multi-delay four-order-cumulant of each frame of voice, and carryingout equal-ratio mean value envelope array extraction in the time domain; and (3) after the time domain and FTSL spectral line signal features of the voice signals are extracted, carrying out automaticclassification on the voice signals by adopting the combined classifier recognition algorithm in combination with the time domain equal-ratio envelope mean value array and the FTSL spectral line features, and outputting the classification result. Compared with the prior art, the method provided by the invention has the advantages that the detection result is objective and accurate, the automaticmeasurement with relatively high degree can be realized, thus reliable reference data are provided for the digital evaluation of pharyngeal fricatives clinically, the accurate medical development demand is conformed, and more accurate and effective signal classification recognition is carried out.

Description

technical field [0001] The invention relates to the field of speech signal processing, in particular to an automatic detection method for pharyngeal fricatives in cleft palate speech based on multi-delay fourth-order cumulant octave band FTSL spectral lines. Background technique [0002] As one of the common compensatory articulation errors, pharyngeal rubbing is second only to glottal stop in incidence. In patients with pharyngeal friction, the tongue retracts to the posterior pharyngeal wall during pronunciation, resulting in narrowing of the pharynx. The airflow from the lungs passes through the narrow channel, and the sound produced by friction is the pharyngeal fricative. The abnormal articulation mainly occurs in the consonant part of Mandarin syllables, because consonants are sounds formed by airflow being obstructed in the oral cavity or pharynx. Pharyngeal fricatives are common in Chinese dialects, but do not appear in normal Mandarin pronunciation. Pharyngeal fri...

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): G10L25/66G10L25/21G10L25/18G10L25/03G06K9/62
CPCG10L25/03G10L25/18G10L25/21G10L25/66G06F18/2411
Inventor 何凌何飞王熙月尹恒
Owner SICHUAN 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
Eureka Blog
Learn More
PatSnap group products