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

Method of conference telephone speech sound selection and composition

A technology of conference call and synthesis method, which is applied in the field of communication, can solve problems such as low work efficiency and poor auditory effect, and achieve the effect of ensuring the amount of information and efficiency

Active Publication Date: 2008-09-10
XIAN DATANG TELECOM
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the problems of poor auditory effect and low work efficiency in the above-mentioned prior art, and provide a method for selecting and synthesizing speech in a conference call, and performing speech synthesis after appropriate selection of participants in the conference call and output to achieve high-definition, high-information conference call services

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
  • Method of conference telephone speech sound selection and composition
  • Method of conference telephone speech sound selection and composition
  • Method of conference telephone speech sound selection and composition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described in detail below in conjunction with specific completed embodiments.

[0036] In this embodiment, the voice signal is sampled at a sampling rate of 8000 Hz, the time unit is set to ΔT=5 ms, the time window Tw=ΔT×n, and the optimal value of n is between 5-50. The maximum number of members allowed to participate in the conference is 128, the number of main speakers N1=1, and the number of secondary speakers N2=5.

[0037] The processing procedure of the speech synthesis selection used in the present embodiment is described in detail below:

[0038] Step 1: Buffer the voice signals output by all the members of the conference call within ΔT, and use the amplitude of the signals to calculate the signal energy. Because the purpose of energy calculation is only to provide a basis for comparison, it is not really necessary to know the specific energy value of the speech signal, so the method used in the present invention to calcul...

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

This invention refers to a selective speech sound synthetic method for telephone conference, which takes the absolute average value of speech sound signal sample of telephone conference as current signal energy of said attendee, then taking n time energy average value as phonetic signal accumulated average energy of said attendee, comparing phonetic signal accumulated average energy of every main speaking attendee and sub speaking attendee and making selection and replacement, updating current speaking attendee list, finally fading phonetic signal and overlapping as phonetic output of telephone conference.

Description

technical field [0001] The invention belongs to the technical field of communication, relates to a conference call service, in particular to a method for selecting and synthesizing conference call voices. Background technique [0002] A conference call, as the name implies, is to hold a conference by telephone. The principle is simply to say that the voice channel output signals of the participants in the same conference are synthesized and used as the voice channel input signals of all participants in the conference call, so that each participant can hear other voice signals. Participants' voices. [0003] The traditional speech synthesis method of a conference call is to directly synthesize all the participants in a conference, that is, to attenuate the voice channel signals of all participants and then superimpose and output them, such as figure 1 shown. The reason for attenuation is to prevent overflow caused by the superposition of multi-channel signals, and the atten...

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): H04M3/56
Inventor 李卫华廖延娜戴明赵占富
Owner XIAN DATANG TELECOM
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