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

Response balance processing method for voice

A processing method and loudness technology, which is applied in the field of loudness equalization processing of speech, to achieve the effect of improving perceived quality, stabilizing perceived speech intensity, and eliminating unstable factors

Inactive Publication Date: 2009-07-15
HANGZHOU HOLINE SCI & TECH
View PDF1 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical solution of this invention is mainly used in the field of speech output, and adjusts the loudness change of the speech segment and the non-speech segment (background sound) output at the same time, but it cannot adjust the loudness of the sound at different times on the time axis when the sound is input or output. suddenly small

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
  • Response balance processing method for voice
  • Response balance processing method for voice
  • Response balance processing method for voice

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] The voice loudness equalization processing method of the present invention is mainly applied to voice output in telephone conferences, video conferences and VOIP, so as to solve the phenomenon that the output voice loudness is sometimes louder and sometimes smaller in practical applications.

[0038] This embodiment takes voice output in VOIP as an example. In this embodiment, loudness equalization is performed on the decoded output speech.

[0039] Such as figure 1 As shown, when the type is judged, the time-frequency transformation of the input signal is performed through the radix-two FFT transformation, and then two sub-bands are divided according to the psychoacoustic model, that is, the signal is divided into two frequency bands of high and low frequencies. The signal energy is calculated in the range of the high and low frequency bands respectively, and the ratio of the high and low frequency energy is calculated, and the ratio of the high and low frequency ener...

Embodiment 2

[0059] The signal type judgment in this embodiment is performed in the time domain, and the specific adjustment process after the type judgment is the same as that in Embodiment 1. The data segment is carried out in the time domain by calculating the short-term signal energy and the short-term zero-crossing rate.

[0060] Such as Figure 4 As shown, high-pass filtering is first performed on the input signal data segment to weaken the signal energy dominated by noise. Next, windowing is performed, and then the average energy of the frame is calculated, and then the short-term energy is used for the preliminary judgment of voice behavior detection (VAD). If the average energy is greater than the threshold, it is judged as the second type of data, and if the average energy is smaller than the threshold, it is judged as low-energy data. VAD smoothing is performed on frames judged as low-energy data, that is, refer to the situation of the first three frames: if the first three fr...

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 present invention discloses a speech loudness equilibrium process method which comprises the following steps: (1) type judgment to speech input signal data block, tag the data block as the first categorical data segment that need loudness adjustment or the second categorical data segment that need no loudness adjustment; (2) context indication mark judgment to the data block, set the context indication marks as 0 initially, if context indication marks of above paragraphs is 0, context indication marks of the first categorical data segment is 1, and adds the initial window function, output after loudness adjustment; the context indication marks is still 0 of the second categorical data segment, then output directly; if the context indication marks of above paragraphs is 1, then output the first categorical data segment after loudness adjustment; set context indication marks 0 of the second categorical data and adds ending window, output after loudness adjustment. The present invention dispels factor of speech output unstable, provides a relative stable apperceive speech intensity, and enhances speech apperceive quality.

Description

technical field [0001] The invention relates to a method for processing speech signals, in particular to a method for processing speech loudness equalization. Background technique [0002] Loudness equalization is relative to human perception. For changing speech, under normal circumstances, you will perceive loudness changes from loudness to loudness. Long-term unstable loudness is likely to cause auditory fatigue and emotional irritability. Subjective quality and efficiency of voice communications. Secondly, in general, the microphones used for recording by users cannot be all professional-grade hardware devices, and the final picked-up voice is affected by the user's experience, resulting in uneven strength. In poor cases, it often causes communication problems. The partner cannot hear what the other party is saying, which seriously affects the overall quality of communication. [0003] The loudness control of the voice signal in the prior art generally simply gains the...

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): H03G9/02H03G9/14
Inventor 金旖青宋钦梅
Owner HANGZHOU HOLINE SCI & TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com