Voice signal processing device and voice signal processing method

A speech signal processing and speech signal technology, applied in speech analysis, instruments, etc., can solve the problems of lowering the recognition degree of the output speech signal and the reduction of the signal-to-noise ratio, so as to avoid the reduction of the signal-to-noise ratio and improve the recognition degree.

Active Publication Date: 2018-07-06
ACER INC
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this processing method can increase the loudness of the output voice signal, when the loudness gain corresponding to the loudness of the noise signal is large, it may cause a decrease in the signal-to-noise ratio, which will reduce the recognition of the output voice signal

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
  • Voice signal processing device and voice signal processing method
  • Voice signal processing device and voice signal processing method
  • Voice signal processing device and voice signal processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] figure 1 is a schematic diagram of a speech signal processing device according to an embodiment of the present invention, please refer to figure 1 . The speech signal processing device includes a filtering unit 102 and a processing unit 104, the filtering unit 102 is coupled to the processing unit 104, wherein the filtering unit 102 can be implemented as a bandpass filter, and the processing unit 104 can be implemented as a central processing unit, for example, However, it is not limited to this.

[0035] The filtering unit 102 is used for filtering the input voice signal SI1 to generate a plurality of filtered signals SF1 - SFN of different frequency bands to the processing unit 104 , wherein N is a positive integer greater than 1. The processing unit 104 can detect the loudness of the input speech signal SI1, and use the loudness of the input speech signal SI1 as the reference loudness. The processing unit 104 can calculate the reference loudness gain corresponding...

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 signal processing device and a voice signal processing method. The method comprises the steps: detecting the loudness of an inputted voice signal, so as to obtain the reference loudness; calculating a reference loudness gain corresponding to each frequency band according to the reference loudness and a wide-dynamic-range compression curve corresponding to each frequency band, and adjusting the loudness of a filtering signal of each frequency band according to the reference loudness gain corresponding to each frequency band. The method can effectively prevent thedecrease of the signal to noise ratio of an outputted voice signal caused by the multi-band wide-dynamic-range compression, and greatly improves the recognition degree of the outputted voice signal.

Description

technical field [0001] The invention relates to a signal processing device, in particular to a voice signal processing device and a voice signal processing method. Background technique [0002] Multi-band Wide Dynamic Range Compression (WDRC) technology is widely used in the range of hearing aids. The main function of wide dynamic range compression is to increase the loudness gain of speech signals with low loudness for easy identification and reduce the loudness Loudness gain of the speech signal to avoid discomfort caused by too loud sound. Generally speaking, multi-band wide dynamic range compression means that each frequency band independently processes speech signals, and the wide dynamic range compression curves of each frequency band are determined by hearing tests based on individual needs. When performing wide dynamic range compression processing on the input speech signal, the loudness of the output speech signal in each frequency band is determined based on the l...

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): G10L21/0332G10L21/0364
CPCG10L21/0332G10L21/0364
Inventor杜博仁张嘉仁曾凯盟
OwnerACER INC