Showing papers by "Vincent Oria published in 2009"

Local summarization and multi-level LSH for retrieving multi-variant audio tracks

Abstract: In this paper we study the problem of detecting and grouping multi-variant audio tracks in large audio datasets. To address this issue, a fast and reliable retrieval method is necessary. But reliability requires elaborate representations of audio content, which challenges fast retrieval by similarity from a large audio database. To find a better tradeoff between retrieval quality and efficiency, we put forward an approach relying on local summarization and multi-level Locality-Sensitive Hashing (LSH). More precisely, each audio track is divided into multiple Continuously Correlated Periods (CCP) of variable length according to spectral similarity. The description for each CCP is calculated based on its Weighted Mean Chroma (WMC). A track is thus represented as a sequence of WMCs. Then, an adapted two-level LSH is employed for efficiently delineating a narrow relevant search region. The "coarse" hashing level restricts search to items having a non-negligible similarity to the query. The subsequent, "refined" level only returns items showing a much higher similarity. Experimental evaluations performed on a real multi-variant audio dataset confirm that our approach supports fast and reliable retrieval of audio track variants.

Multi-version music search using acoustic feature union and exact soft mapping

Abstract: Research on audio-based music retrieval has primarily concentrated on refining audio features to improve search quality. However, much less work has been done on improving the time efficiency of music audio searches. Representing music audio documents in an indexable format provides a mechanism for achieving efficiency. To address this issue, in this work Exact Locality Sensitive Mapping (ELSM) is suggested to join the concatenated feature sets and soft hash values. On this basis we propose audio-based music indexing techniques, ELSM and Soft Locality Sensitive Hash (SoftLSH) using an optimized Feature Union (FU) set of extracted audio features. Two contributions are made here. First, the principle of similarity-invariance is applied in summarizing audio feature sequences and utilized in training semantic audio representations based on regression. Second, soft hash values are pre-calculated to help locate the searching range more accurately and improve collision probability among features similar to each other. Our algorithms are implemented in a demonstration system to show how to retrieve and evaluate multi-version audio documents. Experimental evaluation over a real "multi-version" audio dataset confirms the practicality of ELSM and SoftLSH with FU and proves that our algorithms are effective for both multi-version detection (online query, one-query vs. multi-object) and same content detection (batch queries, multi-queries vs. one-object).

Energy-Efficient Evaluation of Multiple Skyline Queries over a Wireless Sensor Network

Abstract: Though skyline queries in wireless sensor networks have been intensively studied in recent years, existing solutions are not optimized for multiple skyline queries as they focus on single full space skyline queries. It is not efficient to individually evaluate skyline queries especially in a wireless sensor network environment where power consumption should be minimized. In this paper, we propose an energy-efficient multi-skyline evaluation (EMSE) algorithm to effectively evaluate multiple skyline queries in wireless sensor networks. EMSE first utilizes a global optimization mechanism to reduce the number of skyline queries and save on query propagation cost and parts of redundant result transmission cost as a consequence. Then, it utilizes a local optimization mechanism to share the skyline results among skyline queries and uses some filtering policies to further eliminate unnecessary data transmission and save the skyline result transmission cost as a consequence. The experimental results show that the proposed algorithm is energy-efficient when evaluating multiple skyline queries over wireless sensor networks.

A partial-order based active cache for recommender systems

Abstract: Recommender systems aim to substantially reduce information overload by suggesting lists of similar items that users may find interesting.Caching has been a useful technique for reducing stress on limited resources and improving response time. In this paper, we propose an 'active caching' technique for recommender systems based on a partial order approach that not only benefits from popularity and temporal locality, but also exploits spatial locality. This approach allows the processing of answers to neighboring non-cached queries in addition to the reporting of cached query results. Test results for several data sets and recommendation techniques show substantial improvement in the cache hit ratio and computational costs, while achieving reasonable recall rates.

GRE: hybrid recommendations for NSDL collections

Abstract: Recommendation systems have been proven to reduce the time and effort required by users to find relevant items, but there are only sporadic reports on their application in digital libraries. The General Recommendation Engine (GRE) is composed of the text search system Lucene augmented by the well-understood content based and collaborative filtering techniques and the first application of knowledge based recommendation in digital libraries to recommend items from 22 National Science Digital Library collections. In this study comprised of 60 subjects, the GRE outperformed the baseline system Lucene in all areas of evaluation.