10th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing

Research Article

Audio Retrieval Based on Perceptual Similarity

Download784 downloads
  • @INPROCEEDINGS{10.4108/icst.collaboratecom.2014.257704,
        author={Teng Zhang and Ji Wu and Dingding Wang and Tao Li},
        title={Audio Retrieval Based on Perceptual Similarity},
        proceedings={10th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing},
        publisher={IEEE},
        proceedings_a={COLLABORATECOM},
        year={2014},
        month={11},
        keywords={audio retrieval perceptual similarity},
        doi={10.4108/icst.collaboratecom.2014.257704}
    }
    
  • Teng Zhang
    Ji Wu
    Dingding Wang
    Tao Li
    Year: 2014
    Audio Retrieval Based on Perceptual Similarity
    COLLABORATECOM
    IEEE
    DOI: 10.4108/icst.collaboratecom.2014.257704
Teng Zhang1, Ji Wu1, Dingding Wang2,*, Tao Li3
  • 1: Tsinghua University
  • 2: Florida Atlantic University
  • 3: Florida International University
*Contact email: wangd@fau.edu

Abstract

Given a short query audio clip, the goal of audio retrieval is to automatically fetch all similar clips from a given audio database. Different from traditional audio similarity which is mainly based on priori knowledge of objective reality, this paper proposes to use a more subjective method to measure the perceptual similarity between audio clips. These perceptual features focus on users’ personal experience, which can be very helpful for audio retrieval across different databases. In addition, indexing and audio matching methods are introduced to speed up the retrieval process. Experimental results on four different datasets are conducted to evaluate the effectiveness and efficiency of our proposed approaches