Unlock instant, AI-driven research and patent intelligence for your innovation.

Speech signal processing method and device

A voice signal and processing method technology, applied in voice analysis, voice recognition, instruments, etc., can solve the problems of great differences in acoustic characteristics and lower voice recognition accuracy, and improve the robustness and experience of voice recognition services. The effect of improving accuracy and improving robustness

Active Publication Date: 2020-02-04
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing speech recognition training lacks noise speech samples, and the acoustic characteristics of noise speech samples and pure speech samples are very different. Therefore, the accuracy of speech recognition in the acoustic model in the related art is very high in a quiet environment, while in noise The accuracy of speech recognition in the environment will be greatly reduced

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
  • Speech signal processing method and device
  • Speech signal processing method and device
  • Speech signal processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0021] In addition, the terms "first" and "second" are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, a feature defined as "first" and "second" may explicitly or implicitly include one or more of these features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0022] Any process or method descriptions in flowcharts or otherwis...

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 method and apparatus. The voice signal processing method comprises the steps: collecting noise sample signals; according to the noise sample signals, processing a preset pure voice sample signal, and obtaining a noise voice sample signal with noise; according to the noise voice sample signal and the pure voice sample signal, training a voice model. The voice signal processing method can greatly improve the accuracy for voice recognition under the noise environment through the voice model and improve the robustness of voice recognition service and the experience of voice recognition service.

Description

technical field [0001] The invention relates to the technical field of voice recognition, in particular to a voice signal processing method and a voice signal processing device. Background technique [0002] Speech recognition refers to the automatic conversion of human speech into corresponding text by machines. In recent years, speech recognition technology has developed rapidly, especially after the deep neural network is applied to speech recognition, the performance of the recognition system has been greatly improved. [0003] In related technologies, the speech recognition process obtains an acoustic model and a language model by training a large number of pure speech samples. The larger the training sample, the higher the accuracy, the better the effect of the obtained acoustic model, and the higher the accuracy of speech recognition. [0004] However, with the development of the mobile Internet, voice input methods are becoming more and more common, and voice users...

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): G10L21/0208G10L15/20
CPCG10L15/20G10L21/0208
Inventor 时雪煜李先刚邹赛赛
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD