Login| Sign Up| Help| Contact|

Patent Searching and Data

Document Type and Number:
WIPO Patent Application WO/2018/234619
Kind Code:
A method, computer-readable medium and apparatus are disclosed for:receiving, via a first track, a near-field audio signal from a near-field microphone;receiving, via a second track, a far-field audio signal from an array comprising one or more far-field microphones, wherein the far-field audio signal comprises audio signal components across one or more channels corresponding respectively to the or each of the far-field microphones; determining, using the near-field audio signal and the or each component of the far-field audio signal, a set of time dependent room impulse response filters, wherein each of the time dependent room impulse response filters is in relation to the near-field microphone and respective the or each of the channels of the microphone array;for one or more channels of the microphone array, filtering the near-field audio signal using one or more room impulse response filters of the respective one or more channels; and augmenting the far-field audio signal by applying the filtered near-field audio signal thereto.

Application Number:
Publication Date:
February 28, 2019
Filing Date:
May 25, 2018
Export Citation:
Click for automatic bibliography generation   Help
International Classes:
H04S7/00; G10K15/12; H03H17/02; H03H17/04; H03H21/00; H04R5/04; H04R29/00
Domestic Patent References:
Foreign References:
Other References:
BARKER, JON ET AL.: "The third 'CHiME' speech separation and recognition challenge: Analysis and outcomes", COMPUTER SPEECH & LANGUAGE, vol. 46, 6 December 2016 (2016-12-06), pages 605 - 626, XP085145200, ISSN: 0885-2308, [retrieved on 20181004], DOI: doi:10.1016/j.csl.2016.10.005
BARKER, JON ET AL.: "The third 'CHiME' speech separation and recognition challenge: Dataset, task and baselines", PROCEEDINGS OF THE 2015 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU 2015), 13 December 2015 (2015-12-13), Scottsdale, AZ, USA, pages 504 - 511, XP032863588, ISBN: 978-1-4799-7291-3
MALEK, JIRI ET AL.: "Semi-blind Source Separation Based on ICA and Overlapped Speech Detection", PROCEEDINGS OF THE 10TH INTERNATIONAL CONFERENCE ON LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION (LVA/ICA 2012, vol. 7191, Tel Aviv, Israel, pages 462 - 469, XP047371457, ISBN: 978-3-642-28551-6, Retrieved from the Internet [retrieved on 20180928]
KOKKINIS, ELIAS ET AL.: "Identification of a Room Impulse Response Using a Close-Microphone Reference Signal", PROCEEDINGS OF THE 128TH AUDIO ENGINEERING SOCIETY (AES) CONVENTION, 22 May 2010 (2010-05-22), London, UK, XP040509408, [retrieved on 20181009]
VINCENT, EMMANUEL ET AL.: "Oracle estimators for the benchmarking of source separation algorithms", SIGNAL PROCESSING, vol. 87, no. 8, 2 February 2007 (2007-02-02), pages 1933 - 1950, XP022034416, ISSN: 0165-1684, [retrieved on 20181004]
FURUYA KEN'ICHI ET AL.: "Robust Speech Dereverberation Using Multichannel Blind Deconvolution With Spectral Subtraction", IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, vol. 15, no. 5, July 2007 (2007-07-01), pages 1579 - 1591, XP011185741, ISSN: 1558-7916, [retrieved on 20181005]
NIKUNEN, JOONAS ET AL.: "Estimation of Time-Varying Room Impulse Responses of Multiple Sound Sources from Observed Mixture and Isolated Source Signals", PROCEEDINGS OF THE 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2018, Calgary, AB, Canada, pages 421 - 425, XP033401799, ISSN: 2379-190X, ISBN: 978-1-5386-4658-8, [retrieved on 20181129]
Attorney, Agent or Firm:
NOKIA TECHNOLOGIES OY et al. (IPR DepartmentKarakaari 7, Espoo, FI)
Download PDF: