TOP > 外国特許検索 > SYSTEM AND METHOD FOR TARGET SOUND SIGNAL RESTORATION

SYSTEM AND METHOD FOR TARGET SOUND SIGNAL RESTORATION UPDATE

外国特許コード F180009664
整理番号 5360
掲載日 2018年11月21日
出願国 世界知的所有権機関(WIPO)
国際出願番号 2017JP019259
国際公開番号 WO 2017204226
国際出願日 平成29年5月23日(2017.5.23)
国際公開日 平成29年11月30日(2017.11.30)
優先権データ
  • 特願2016-102063 (2016.5.23) JP
発明の名称 (英語) SYSTEM AND METHOD FOR TARGET SOUND SIGNAL RESTORATION UPDATE
発明の概要(英語) Provided are a system and a method for voice signal restoration that are able to restore, with a high degree of accuracy, a target sound signal from a noise-containing sound signal without using prior information. A common sparse component estimation unit 7 that receives, as input, amplitude spectrograms of M channels is provided for estimating a common sparse component containing a sparse time-frequency component which is highly likely to be commonly included in the amplitude spectrograms of the largest number of channels among the M channels. A phase restoration unit 9 restores a phase of the common sparse component so as to obtain a target sound complex spectrogram. A target sound signal conversion unit 13 converts the target sound complex spectrogram into a target sound signal, which is a temporal signal.
従来技術、競合技術の概要(英語) BACKGROUND ART
Is the non-patent document 1, the target speech signal and noise of a mixture of multi-channel acoustic signal observed, only the target speech signal can be separated from the disclosed technology.
Is the non-patent document 2, a plurality of microphones of the acoustic signal collected by a plurality of channels to restore the audio signal included in the disclosed technique. Specifically, the microphone array is mounted and a flexible rope-shaped robot recorded in the audio signal for speech enhancement, microphone arrays (robust principal component analysis) RPCA applied to noise suppression method is disclosed. In this technique, first applied to the respective channels RPCA, a common component of each channel in order to extract the center value is taken to integrate.
The technique described in Non-Patent Document 3 is, without a priori information of the noise of the noise sound from the low-rank property and enhancing the sparsity of the sound.
The patent document 1 (Patent Publication 5752324) of the technique, a single channel sound signal (accidental) from the impulse noise is removed. This technique, the performance of removing impulsive noise is high, while the continuous non-stationary noise is not assumed (low-rank noise) deterioration of the performance.
Patent Document 2 (JP-2009-116275 publication) in the technique, a single channel sound signal from the minimum mean square error (MMSE) method on the basis of the noise suppression. MMSE is, it is assumed that the stationarity of the noise for the suppression of non-stationary noise and the performance is degraded.
Patent Document 3 (Japanese Laid-open 2014-503849) in the technique described in, the noise source is disposed near the microphone of the mobile device, to actively utilize the information of the present microphone audio enhancement technique is disclosed. Of the present technology, have been identified and the position of the noise source, the child that the microphone is located near the noise source.
Patent Document 4 (Japanese Laid-open 2015-095897) is, the video signal and extracting low-rank component in the sparse component, and a background image for the image of the moving objects has been disclosed a technology. Is applied to the sound emphasis with this approach is possible, a portion of the audio recording microphone an obstacle or the like cannot be sufficiently increased when the performance degradation.
Patent Document 5 (Japanese Laid-open 2014-058399) in the technique described, any number of the sound source signal of a mixture of multi-channel acoustic signal observed from the separating and extracting the sound source signal. Of the present technology, the position of each microphone and the sound source position is fixed and assumed, and the performance is degraded when they move.
  • 出願人(英語)
  • ※2012年7月以前掲載分については米国以外のすべての指定国
  • KYOTO UNIVERSITY
  • 発明者(英語)
  • BANDO Yoshiaki
  • YOSHII Kazuyoshi
  • ITOYAMA Katsutoshi
  • OKUNO Hiroshi
国際特許分類(IPC)
指定国 National States: AE AG AL AM AO AT AU AZ BA BB BG BH BN BR BW BY BZ CA CH CL CN CO CR CU CZ DE DJ DK DM DO DZ EC EE EG ES FI GB GD GE GH GM GT HN HR HU ID IL IN IR IS JP KE KG KH KN KP KR KW KZ LA LC LK LR LS LU LY MA MD ME MG MK MN MW MX MY MZ NA NG NI NO NZ OM PA PE PG PH PL PT QA RO RS RU RW SA SC SD SE SG SK SL SM ST SV SY TH TJ TM TN TR TT TZ UA UG US UZ VC VN ZA ZM ZW
ARIPO: BW GH GM KE LR LS MW MZ NA RW SD SL SZ TZ UG ZM ZW
EAPO: AM AZ BY KG KZ RU TJ TM
EPO: AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
OAPI: BF BJ CF CG CI CM GA GN GQ GW KM ML MR NE SN ST TD TG
ライセンスをご希望の方、特許の内容に興味を持たれた方は、下記までご連絡ください。

PAGE TOP

close
close
close
close
close
close