Method for speech enhancement

A technology for speech enhancement and noisy speech, applied in speech analysis, instruments, etc., can solve the problems of large amount of calculation and storage space, high cost, high hardware, etc., achieve outstanding attenuation effect, ensure intelligibility, and improve attenuation effect

Active Publication Date: 2009-12-09
AAC TECH PTE LTD +1
View PDF0 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The amount of calculation and storage space required by the existing related speech enhancement algorithms are relatively large, the requirements for hardware are relatively high, and the area of ​​silicon required when making a dedicated chip is also relatively large, so that the cost is relatively high, and the cost is reduced. The noise effect is not very good

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 for speech enhancement
  • Method for speech enhancement
  • Method for speech enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be further described below in conjunction with drawings and embodiments.

[0021] The voice enhancement method algorithm of the present invention can be integrated in a dedicated chip processor, and a real-time voice enhancement system is formed through the interface data transmission between the chip processor and the corresponding sound collection device. The speech signal is collected by the sound collection device, and then directly processed by the speech enhancement algorithm in the chip processor to obtain a signal with an enhanced signal-to-noise ratio, which is output for secondary use. In this embodiment, the sound collection device may be a microphone, and the analog signal collected by the microphone needs to be converted into a digital signal for processing by the chip processor.

[0022] The method for speech enhancement of the present invention, it comprises the following steps:

[0023] (1), the sound collection device is coll...

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 method for achieving speech enhancement, which comprises the following steps: performing frame separation and pre-emphasis processing on a noisy speech signal, and transforming the noisy speech signal into a frequency domain; dividing the noisy speech signal into a plurality of frequency bands, calculating the signal energy of each frequency channel, and updating the estimated value of the noise energy; calculating the posteriori signal-to-noise ratio of the current frame, and the estimated value of the priori signal-to-noise ratio; calculating the attenuation factor of each frequency band, and processing the attenuation factor to obtain a speech signal with increased signal-to-noise ratio; and transforming the speech signal after the processing into a time domain, and outputting the speech signal.

Description

【Technical field】 [0001] The invention relates to a method for voice enhancement. 【Background technique】 [0002] Due to the existence of a large amount of environmental noise, the signal-to-noise ratio of the voice signal collected by the sound collection system, such as a microphone microphone, is generally not high enough. In order to collect a speech signal with a high signal-to-noise ratio, usually, a speech signal within a certain range is collected by using a directional microphone, or a speech enhancement method is used to improve the signal-to-noise ratio of the speech signal. [0003] The amount of calculation and storage space required by the existing relevant speech enhancement algorithms are relatively large, and the requirements for hardware are relatively high. The noise effect is not very ideal. [0004] Therefore, it is necessary to study a new speech enhancement method in order to achieve a good noise reduction effect. 【Content of invention】 [0005] T...

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): G10L21/02G10L21/0232
Inventor 叶利剑
Owner AAC TECH PTE LTD
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap