The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este artigo investiga técnicas de indexação adequadas para permitir a recuperação eficiente de áudio baseada em conteúdo em grandes bancos de dados acústicos. Para tornar um mecanismo de recuperação baseado em índice aplicável ao conteúdo de áudio, investigamos o design do Hashing Sensível à Localidade (LSH) e a comparação parcial da sequência. Propomos uma estrutura de recuperação de áudio rápida e eficiente de consulta por conteúdo e desenvolvemos um sistema de recuperação de áudio. Com base nesta estrutura, quatro esquemas diferentes de recuperação de áudio, LSH-Programação Dinâmica (DP), LSH-Sparse DP (SDP), LSH Euclidiano Exato (E2LSH)-DP, E2LSH-SDP são introduzidos e avaliados para melhor compreender o desempenho dos algoritmos de recuperação de áudio. Os resultados experimentais indicam que comparado com o DP tradicional e os outros três esquemas competitivos, E2O LSH-SDP apresenta a melhor compensação em termos de tempo de resposta, precisão de recuperação e custo de computação.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Yi YU, Kazuki JOE, J. Stephen DOWNIE, "Efficient Query-by-Content Audio Retrieval by Locality Sensitive Hashing and Partial Sequence Comparison" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 6, pp. 1730-1739, June 2008, doi: 10.1093/ietisy/e91-d.6.1730.
Abstract: This paper investigates suitable indexing techniques to enable efficient content-based audio retrieval in large acoustic databases. To make an index-based retrieval mechanism applicable to audio content, we investigate the design of Locality Sensitive Hashing (LSH) and the partial sequence comparison. We propose a fast and efficient audio retrieval framework of query-by-content and develop an audio retrieval system. Based on this framework, four different audio retrieval schemes, LSH-Dynamic Programming (DP), LSH-Sparse DP (SDP), Exact Euclidian LSH (E2LSH)-DP, E2LSH-SDP, are introduced and evaluated in order to better understand the performance of audio retrieval algorithms. The experimental results indicate that compared with the traditional DP and the other three compititive schemes, E2LSH-SDP exhibits the best tradeoff in terms of the response time, retrieval accuracy and computation cost.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.6.1730/_p
Copiar
@ARTICLE{e91-d_6_1730,
author={Yi YU, Kazuki JOE, J. Stephen DOWNIE, },
journal={IEICE TRANSACTIONS on Information},
title={Efficient Query-by-Content Audio Retrieval by Locality Sensitive Hashing and Partial Sequence Comparison},
year={2008},
volume={E91-D},
number={6},
pages={1730-1739},
abstract={This paper investigates suitable indexing techniques to enable efficient content-based audio retrieval in large acoustic databases. To make an index-based retrieval mechanism applicable to audio content, we investigate the design of Locality Sensitive Hashing (LSH) and the partial sequence comparison. We propose a fast and efficient audio retrieval framework of query-by-content and develop an audio retrieval system. Based on this framework, four different audio retrieval schemes, LSH-Dynamic Programming (DP), LSH-Sparse DP (SDP), Exact Euclidian LSH (E2LSH)-DP, E2LSH-SDP, are introduced and evaluated in order to better understand the performance of audio retrieval algorithms. The experimental results indicate that compared with the traditional DP and the other three compititive schemes, E2LSH-SDP exhibits the best tradeoff in terms of the response time, retrieval accuracy and computation cost.},
keywords={},
doi={10.1093/ietisy/e91-d.6.1730},
ISSN={1745-1361},
month={June},}
Copiar
TY - JOUR
TI - Efficient Query-by-Content Audio Retrieval by Locality Sensitive Hashing and Partial Sequence Comparison
T2 - IEICE TRANSACTIONS on Information
SP - 1730
EP - 1739
AU - Yi YU
AU - Kazuki JOE
AU - J. Stephen DOWNIE
PY - 2008
DO - 10.1093/ietisy/e91-d.6.1730
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2008
AB - This paper investigates suitable indexing techniques to enable efficient content-based audio retrieval in large acoustic databases. To make an index-based retrieval mechanism applicable to audio content, we investigate the design of Locality Sensitive Hashing (LSH) and the partial sequence comparison. We propose a fast and efficient audio retrieval framework of query-by-content and develop an audio retrieval system. Based on this framework, four different audio retrieval schemes, LSH-Dynamic Programming (DP), LSH-Sparse DP (SDP), Exact Euclidian LSH (E2LSH)-DP, E2LSH-SDP, are introduced and evaluated in order to better understand the performance of audio retrieval algorithms. The experimental results indicate that compared with the traditional DP and the other three compititive schemes, E2LSH-SDP exhibits the best tradeoff in terms of the response time, retrieval accuracy and computation cost.
ER -