Title:
ロバストかつインバリアントな音声パターンマッチング
Document Type and Number:
Japanese Patent JP4425126
Kind Code:
B2
Abstract:
The present invention provides an innovative technique for rapidly and accurately determining whether two audio samples match, as well as being immune to various kinds of transformations, such as playback speed variation. The relationship between the two audio samples is characterized by first matching certain fingerprint objects derived from the respective samples. A set (230) of fingerprint objects (231,232), each occurring at a particular location (242), is generated for each audio sample (210). Each location (242) is determined in dependence upon the content of the respective audio sample (210) and each fingerprint object (232) characterizes one or more local features (222) at or near the respective particular location (242). A relative value is next determined for each pair of matched fingerprint objects. A histogram of the relative values is then generated. If a statistically significant peak is found, the two audio samples can be characterized as substantially matching.
Inventors:
Wang, Avery Lee-Chun
Calvert, Daniel
Calvert, Daniel
Application Number:
JP2004500283A
Publication Date:
March 03, 2010
Filing Date:
April 18, 2003
Export Citation:
Assignee:
Landmark Digital Services LLC
International Classes:
G10L15/02; G06K9/00; G10H1/00; G10L15/10; G10L17/00; G10L17/02; G10L25/51; G10L15/20
Domestic Patent References:
JP2000172292A | ||||
JP1237600A |
Foreign References:
WO2002011123A1 | ||||
WO1998034216A1 |
Attorney, Agent or Firm:
Yoichi Oshima