Sound source distance determination method and device

A distance and sound source technology, which is applied in the field of sound source distance determination method and device, can solve the problems of high investment cost of a single microphone and inaccurate distance measurement of multiple microphones, and achieve the effect of solving inaccurate distance measurement and reducing costs

Active Publication Date: 2021-03-05
ANHUI IFLYTEK INTELLIGENT SYST
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a sound source distance determination method and device to solve the problem that the existing single microphone can only use a third-party sensor for distance measurement and the problem of high investment cost, and the fact that multiple microphones are limited by the centralized layout of the microphone array hardware The problem of inaccurate distance measurement caused by

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
  • Sound source distance determination method and device
  • Sound source distance determination method and device
  • Sound source distance determination method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the drawings and implementations.

[0072] Aiming at the problems in the prior art, the embodiment of the present invention provides a method and device for determining the distance of a sound source, which uses a machine learning-based approach to solve the problem of the traditional single-mic only being able to use a third-party sensor for distance measurement. The problem of high cost also solves the problem of inaccurate distance measurement caused by the traditional multi-microphone limited by the centralized hardware layout of the microphone array.

[0073] Specifically, first extract the spectral features from the received user voice signal, and use the spectral features to obtain the reverberation impact function coefficient features and t...

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 discloses a method and device for determining the distance of a sound source. The method comprises: receiving a voice signal of a user; extracting the frequency spectrum feature of the voice signal; inputting the frequency spectrum feature into a pre-built voice separation model to obtain the voice signal The reverberation shock function coefficient feature; Input the spectral feature into the speech environment analysis model built in advance to obtain the speech environment information of the speech signal; Based on the reverberation shock function coefficient feature, speech environment information and pre-built The source distance judgment model obtains the distance information between the user's voice and the microphone. With the present invention, the accuracy of distance measurement can be improved without resorting to a third-party sensor.

Description

technical field [0001] The invention relates to the field of speech signal processing, in particular to a sound source distance determination method and device. Background technique [0002] With the advancement of artificial intelligence technology, human-computer voice interaction has also made great progress, and various voice assistant APPs and human-computer interaction robots are booming. Speech recognition is one of the essential functions in voice interaction, and its recognition effect largely depends on the recording quality. When the recording quality of existing speech recognition devices is poor, the overall recognition effect will drop sharply, which seriously affects the user experience. . Therefore, as one of the methods to improve the quality of voice recording: reminding and / or correcting the user's voice input habit (such as being closer to the microphone) according to the user's voice input distance is particularly important for voice recognition and eve...

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): G10L25/18G10L25/30G10L25/75G10L21/028
CPCG10L21/028G10L25/18G10L25/30G10L25/75
Inventor 喻涛潘嘉王海坤王智国胡国平胡郁刘庆峰
Owner ANHUI IFLYTEK INTELLIGENT SYST
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