Title:
PITCH ESTIMATION AND AUDIO SOURCE SEPARATION
Document Type and Number:
WIPO Patent Application WO/2011/029048
Kind Code:
A3
Abstract:
The present invention relates to co-channel audio source separation. In one embodiment a first frequency-related representation of plural regions of the acoustic signal is prepared over time, and a two-dimensional transform of plural two- dimensional localized regions of the first frequency-related representation, each less than an entire frequency range of the first frequency related representation, is obtained to provide a two-dimensional compressed frequency-related representation with respect to each two dimensional localized region. For each of the plural regions, at least one pitch is identified. The pitch from the plural regions is processed to provide multiple pitch estimates over time. In another embodiment, a mixed acoustic signal is processed by localizing multiple time-frequency regions of a spectrogram of the mixed acoustic signal to obtain one or more acoustic properties. A separate pitch estimate of each of the multiple acoustic signals at a time point are provided by combining the one or more acoustic properties. At least one of the multiple acoustic signals is recovered using the separate pitch estimates.
Inventors:
WANG TIANYU (US)
QUATIERI THOMAS F JR (US)
QUATIERI THOMAS F JR (US)
Application Number:
PCT/US2010/047888
Publication Date:
April 28, 2011
Filing Date:
September 03, 2010
Export Citation:
Assignee:
MASSACHUSETTS INST TECHNOLOGY (US)
WANG TIANYU (US)
QUATIERI THOMAS F JR (US)
WANG TIANYU (US)
QUATIERI THOMAS F JR (US)
International Classes:
G10L25/90; G10L25/93; G10L21/02
Foreign References:
| US20040054527A1 | 2004-03-18 |
Other References:
WANG T T, QUATIERI, T F: "2-D processing of speech for multi-pitch analysis", INTERSPEECH 2009, 6 September 2009 (2009-09-06) - 10 September 2009 (2009-09-10), XP002621781
WANG T T ET AL: "Towards co-channel speaker separation BY 2-D demodulation of spectrograms", APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS, 2009. WASPAA '09. IEEE WORKSHOP ON, IEEE, PISCATAWAY, NJ, USA, 18 October 2009 (2009-10-18), pages 65 - 68, XP031575151, ISBN: 978-1-4244-3678-1
WANG T T ET AL: "Towards co-channel speaker separation BY 2-D demodulation of spectrograms", APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS, 2009. WASPAA '09. IEEE WORKSHOP ON, IEEE, PISCATAWAY, NJ, USA, 18 October 2009 (2009-10-18), pages 65 - 68, XP031575151, ISBN: 978-1-4244-3678-1
Attorney, Agent or Firm:
SMITH, James, M. et al. (Brook Smith & Reynolds, P.C.,530 Virginia Rd, P.O. Box 913, Concord MA, US)
Download PDF:
Previous Patent: REAL TIME CONFIGURATION AND PROVISIONING FOR A CARRIER ETHERNET EXCHANGE
Next Patent: POWER SUPPLY SYSTEM FOR A BUILDING
Next Patent: POWER SUPPLY SYSTEM FOR A BUILDING