Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD FOR EXTRACTING FEATURE FROM ACOUSTIC SIGNAL GENERATED FROM ONE SOUND SOURCE AND METHOD FOR EXTRACTING FEATURE FROM ACOUSTIC SIGNAL GENERATED FROM A PLURALITY OF SOUND SOURCES
Document Type and Number:
Japanese Patent JP2003015684
Kind Code:
A
Abstract:

To provide a computerized method for extracting features from acoustic signals generated from one or a plurality of sound sources.

The acoustic signal are first windowed and filtered to produce a spectral envelope for each source. The dimensionality of the spectral envelope is then reduced to produce a set of features for the acoustic signal. The features in the set are clustered to produce a group of features for each of the sources. The features in each group include spectral features and corresponding temporal features characterizing each source. Each group of features is a quantitative descriptor that is also associated with a qualitative descriptor. Hidden Markov models are trained with sets of known features and stored in a database. The database can then be indexed by sets of unknown features to select or recognize like acoustic signals.


Inventors:
MICHAEL A KASEI
Application Number:
JP2002000146685
Publication Date:
January 17, 2003
Filing Date:
May 21, 2002
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
MITSUBISHI ELECTRIC RES LAB
International Classes:
G10L15/10; G10L11/00; G10L15/02; G10L15/06; G10L15/14; G10L19/00; G10L21/02; (IPC1-7): G10L15/10; G10L11/00; G10L15/02; G10L15/06; G10L15/14
Attorney, Agent or Firm:
曾我 道照 (外6名)