Speech analyzing apparatus, speech analyzing/synthesizing apparatus, correction rule information generating apparatus, speech analyzing system, speech analyzing method, correction rule information generating method, and program

An analysis device and sound technology, applied in speech analysis, instruments, etc., can solve the problems of band-pass signal autocorrelation value reduction, difficulty in seeing high-order harmonics, buried sound signals, etc.

Inactive Publication Date: 2011-03-02
PANASONIC INTELLECTUAL PROPERTY CORP OF AMERICA
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, as shown in Figure 18 (b), in In the case of overlapping background noise, the sound signal is buried by the background noise, making it difficult to see higher harmonics
Therefore, in the prior art, the autocorrelation value of the band-pass signal is lowered, resulting in the calculation of more aperiodic components than actually

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 analyzing apparatus, speech analyzing/synthesizing apparatus, correction rule information generating apparatus, speech analyzing system, speech analyzing method, correction rule information generating method, and program
  • Speech analyzing apparatus, speech analyzing/synthesizing apparatus, correction rule information generating apparatus, speech analyzing system, speech analyzing method, correction rule information generating method, and program
  • Speech analyzing apparatus, speech analyzing/synthesizing apparatus, correction rule information generating apparatus, speech analyzing system, speech analyzing method, correction rule information generating method, and program

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] figure 1 It is a block diagram showing an example of the functional configuration of the audio analysis device 100 in Embodiment 1 of the present invention.

[0053] figure 1 The sound analysis device 100 in the present invention is based on the input signal representing the mixed sound of background noise and sound, and analyzes the aperiodic component contained in the sound, and the sound analysis device 100 includes: a noise interval identification part 101, a soundless judgment unit 102, fundamental frequency normalization unit 103, frequency band division unit 104, correlation function calculation units 105a, 105b, 105c, signal-to-noise ratio (SNR: SignalNoise Ratio) calculation units 106a, 106b, 106c, correction amount determination units 107a, 107b , 107c, and aperiodic component ratio calculation units 108a, 108b, 108c.

[0054] The audio analysis device 100 can also be realized as a computer system including, for example, a central processing unit, a storag...

Embodiment 2

[0199] In Embodiment 1, it was explained that the amount of influence on the autocorrelation value of the sound due to noise (that is, the autocorrelation value calculated for the sound and the autocorrelation calculated for the mixed sound of the sound and noise) The magnitude of the difference between values) and the signal-to-noise ratio of the sound and the noise have a certain relationship that can be represented by appropriate correction rule information (for example, an approximate function represented by a third-degree polynomial).

[0200] In addition, the case where the correction amount determination units 107a-107c of the sound analysis device 100 correct the autocorrelation value calculated for the mixed sound of the background noise and the sound by the correction amount is described. The correction amount is determined according to the signal-to-noise ratio according to the correction rule information, so as to calculate the autocorrelation value of the noise-fre...

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

A speech analyzing apparatus for precisely analyzing non-periodic components of speech in a practical environment where background noise is existent comprises a frequency band dividing unit (104) that frequency divides an input signal, which is representative of mixture sounds in which speech is mixed with background noise, into a plurality of bandpass signals; a noise section identifying unit (101) that discriminates between the noise and speech sections of the input signal; SNR calculating units (106a-106c) each of which calculates an S / N ratio that is a ratio of the power in the speech section of a respective bandpass signal to the power in the noise section thereof; correlation function calculating units (105a-105c) each of which calculates an autocorrelation function of the respective bandpass signal in the speech section; correction amount deciding units (107a-107c) each of which decides a correction amount based on the respective calculated S / N ratio; and non-periodic component ratio calculating units (108a-108c) each of which calculates, based on the decided correction amount and the calculated autocorrelation function, a ratio of the non-periodic component included in the speech for the respective one of the plurality of frequency bands.

Description

technical field [0001] The present invention relates to techniques for analyzing non-periodic components of sound. technical background [0002] In recent years, with the development of sound generation technology, it has become possible to create synthetic sounds with very high sound quality. Such synthesized voices are mainly used, for example, to read news sentences in the intonation of an announcer. [0003] On the one hand, some kind of special voice (highly synthesized voice with personal reproducibility or special rhythm or voice with the tone of a high school girl or Kansai dialect) is becoming popular in the services provided in mobile phone services, etc. High-quality synthetic sound), integrated into one content, for example, replacing electric bells with voice messages of famous people. [0004] Another aspect of the use of synthetic voices is that in order to increase the enjoyment of communication between individuals, there is also an increasing demand for cr...

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): G10L11/00G10L11/04G10L25/51G10L25/03G10L25/06G10L25/90G10L25/93
CPCG10L21/0208G10L19/0204
Inventor 广濑良文釜井孝浩
Owner PANASONIC INTELLECTUAL PROPERTY CORP OF AMERICA
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