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

Audio sentence boundary detection method

A boundary detection and sentence technology, applied in speech analysis, speech recognition, instruments, etc., to achieve the effect of flexibility, simple method and strong practicability

Inactive Publication Date: 2018-08-03
FUZHOU UNIV
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are very few studies related to singing audio sentence segmentation, and some of the work is essentially aimed at the segmentation of text sentences.

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
  • Audio sentence boundary detection method
  • Audio sentence boundary detection method
  • Audio sentence boundary detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0034] The present invention proposes an audio sentence boundary detection method, such as figure 1 The shown is mainly divided into three steps: firstly, use the improved spectral entropy algorithm based on CQT to perform routine endpoint detection on the singing signal, then analyze and classify the sentence endpoints in combination with the K-Means algorithm, and finally analyze the sentence boundary sequence to the singing signal to split. details as follows:

[0035] Step S1: Calculating the CQT spectrum of the singing voice audio: First, filter the entire singing voice audio signal, pre-emphasize, normalize and other preprocessing, and then perform CQT transformation on the pre-processed singing voice x(n) to obtain the frequency domain signal X CQT (k):

[0036]

[0037] in, is the window length N k Hanning window function...

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 an audio sentence boundary detection method. The method comprises the following steps: in accordance with a phrasing problem on song audio frequency, implementing time-frequency transformation on a sung song via CQT in accordance with human ear auditory perception characteristics, and implementing fine grit end detection on the sung song via a sub-band spectral entropy method; and on the basis, implementing clustering analysis based on a K-means algorithm so as to obtain end positions of sub-sentences based on the characteristics that sentences of the sung song keep relatively long pause and pronunciation intervals therebetween, so that boundary points between unaccompanied audio sentences can be obtained relatively well, and self-adapting to musics of different rhythms can be achieved. The audio sentence boundary detection method provided by the invention is simple, flexible to implement and relatively strong in practicability.

Description

Technical field [0001] The invention relates to the field of audio segmentation, in particular to an audio sentence boundary detection method. Background technique [0002] Audio segmentation is a crucial processing technology in fields such as music retrieval, speech recognition, and audio scene analysis. In the face of tens of thousands of audio data in the current big data era, if the audio data stream can be automatically segmented according to different contents, it will greatly simplify manual operations and improve efficiency. However, there is currently very little research related to singing audio segmentation, and some of the work is essentially aimed at segmenting text sentences. Therefore, studying how to perform sentence boundary detection on a cappella vocal audio has very important practical application value. Contents of the invention [0003] The purpose of the present invention is to provide an audio sentence boundary detection method that can analyze 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
IPC IPC(8): G10L15/04G10L15/08G10L25/18G10L25/45G06K9/62
CPCG10L15/04G10L15/08G10L25/18G10L25/45G06F18/23213
Inventor 张栋彭建云肖小强
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com