Paper: | AE-P6.9 | ||
Session: | Audio for Multimedia and Networks | ||
Time: | Friday, May 21, 13:00 - 15:00 | ||
Presentation: | Poster | ||
Topic: | Audio and Electroacoustics: Audio for Multimedia | ||
Title: | IMPROVE AUDIO REPRESENTATION BY USING FEATURE STRUCTURE PATTERNS | ||
Authors: | Rui Cai; Tsinghua University | ||
Lie Lu; Microsoft Research Asia | |||
Hong-Jiang Zhang; Microsoft Research Asia | |||
Lian-Hong Cai; Tsinghua University | |||
Abstract: | Although statistical characteristics of audio features are widely used for audio representation in most of current audio analysis systems and have been proved to be effective, they only utilized the average feature variations over time, and thus lead to ambiguities in some cases. Structure patterns, which describe the representative structure characteristics of both temporal and spectral features, are proposed to improve audio representation. In this paper, three kind structure patterns, including energy envelope pattern, sub-band spectral shape pattern and harmonicity prominence pattern, are proposed or refined, as successive development of our previous work [1]. Evaluations on a content-based audio retrieval system with more than 1500 clips showed very encouraging results. | ||
Back |
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops