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

Specific sound event retrieval and positioning method based on sequence classification

A sound and event technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as weakening the role of video and image monitoring, and achieve the effect of improving detection performance

Active Publication Date: 2020-05-15
FUZHOU UNIV
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] Although single video image monitoring currently occupies the main position in actual home security applications, there are also some disadvantages. For example, when the lighting conditions are poor or at night, or when the target object is blocked by other things, the role of video image monitoring greatly weakened, while audio monitoring is not affected by this

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
  • Specific sound event retrieval and positioning method based on sequence classification
  • Specific sound event retrieval and positioning method based on sequence classification
  • Specific sound event retrieval and positioning method based on sequence classification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0049] It should be pointed out that the following detailed descriptions are all exemplary, and are intended to provide further explanation to the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0050] It should be noted that the terminology used here is only for describing specific implementations, and is not intended to limit the exemplary implementations according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should also be understood that when the terms "comprises" and / or "comprises" are used in this specification, they indicate There are features, steps, operations, means...

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 relates to a specific sound event retrieval and positioning method based on sequence classification. According to the method, important context information is concerned by utilizing thetime sequence and attention mechanism of sound so as to extract sound deep features of a specific target sound event, and then a specific sound event retrieval network is trained by combining multi-task learning with regression loss and classification loss. When specific audio event retrieval and positioning are carried out on a given audio file; the method comprises the following steps: firstly,inputting Mel characteristic energy of a sound segment to be detected into a sound retrieval model to obtain a retrieval result of a specific sound event of each sound segment, then positioning startand stop audio frames appearing in the specific sound event through post-processing, and finally obtaining complete specific sound event retrieval and positioning information of an audio file throughsmoothing processing.

Description

technical field [0001] The invention relates to the field of audio signal processing, in particular to a method for searching and locating specific sound events based on sequence classification. Background technique [0002] In order to better introduce the concept of pitch range, some basic concepts are introduced first. [0003] Audio: Audio signals are generally divided into two categories: speech signals and non-speech signals. Speech is mainly the sound that human beings make through the vocal organs during speech communication; non-speech includes various sounds of nature, and the scope is very wide. [0004] Sound event: A sound event refers to an audio segment with certain semantics or content in the audio stream, for example, the sound of wind in the street, the sound of pedestrians walking and talking, and the sound of driving cars, etc. [0005] Sound Event Detection (SED), also known as audio event detection, refers to finding sound events of interest in a give...

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): G10L15/08G10L15/183G10L19/04G10L25/18G10L25/24G10L25/45
CPCG10L15/08G10L15/183G10L25/24G10L25/18G10L25/45G10L19/04
Inventor 余春艳刘煌吴长轩
Owner FUZHOU UNIV
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