A General Framework of Progressive Filtering and Its Application to Query by Singing/Humming

Jang, Jyh-Shing Roger; Lee, Hong-Ru

doi:10.1109/tasl.2007.913035

Cited by 42 publications

(18 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5). Initially, for each candidate x, we compute the lower bound LB_Keogh 1 (x, y) (see lines [8][9][10][11][12][13][14][15]. If this lower bound is sufficiently large, the candidate is discarded (see line 16), otherwise we add LB_Keogh 1 (y, H(x, y)) to LB_Keogh 1 (x, y), in effect computing LB_Improved 1 (x, y) (see lines [17][18][19][20][21][22].…”

Section: Corollary 2 Given Two Equal-length Time Series X and Y Andmentioning

confidence: 99%

Faster retrieval with a two-pass dynamic-time-warping lower bound

Lemire¹

2009

Pattern Recognition

168

119

View full text Add to dashboard Cite

The dynamic time warping (DTW) is a popular similarity measure between time series. The DTW fails to satisfy the triangle inequality and its computation requires quadratic time. Hence, to find closest neighbors quickly, we use bounding techniques. We can avoid most DTW computations with an inexpensive lower bound (LB_Keogh). We compare LB_Keogh with a tighter lower bound (LB_Improved). We find that LB_Improved-based search is faster. As an example, our approach is 2-3 times faster over random-walk and shape time series.

show abstract

Section: Corollary 2 Given Two Equal-length Time Series X and Y Andmentioning

confidence: 99%

Faster retrieval with a two-pass dynamic-time-warping lower bound

Lemire¹

2009

Pattern Recognition

168

119

View full text Add to dashboard Cite

show abstract

“…Very recently, Roger Jang and Hong-Ru Lee [24] proposed a mathematical formulation and design methodology of progressive filtering (PF) for multimedia information retrieval. In [24], they conducted an evaluation on massive datasets: the QBSH corpus [14], consisting of 2,797 singing/humming snippets, and a database consisting of about 13,000 songs.…”

Section: Audio Transcription Systemmentioning

confidence: 99%

M-MUSICS: an intelligent mobile music retrieval system

2010

View full text Add to dashboard Cite

Accurate voice humming transcription and efficient indexing and retrieval schemes are essential to a large-scale humming-based audio retrieval system. Although much research has been done to develop such schemes, their performance in terms of precision, recall, and F-measure, among all similarity metrics, are still unsatisfactory. In this paper, we propose a new voice query transcription scheme. It considers the following features: note onset detection using dynamic threshold methods, fundamental frequency (F0) acquisition of each frame, and frequency realignment using K-means. We use a popularity-adaptive indexing structure called frequently accessed index (FAI) based on frequently queried tunes for indexing purposes. In addition, we propose a semi-supervised relevance feedback and query reformulation scheme based on a genetic algorithm to improve retrieval efficiency. In this paper, we extend our efforts to mobile multimedia environments and develop a mobile audio retrieval system. Experiments show our system performs satisfactory in wireless mobile multimedia environments.

show abstract

“…Raghavan et al presented a progressive evaluation framework ProgXe to progressively generate query results early and often for mulit-criteria decision support queries (Raghavan and Rundensteiner 2010). Jang et al designed a methodology of progressive filtering (PF) for multimedia information retrieval, whose applications were called the melody recognition (Jang and Lee 2008). Kache et al proposed a progressive optimization technique for federated queries, which were regular relational queries accessing data on one or more remote relational or non-relational data sources, possibly combining them with tables stored in the federated DBMS server (Kache et al 2006).…”

Section: Introductionmentioning

confidence: 99%

Optimization of generic progressive queries based on dependency analysis and materialized views

Zhu

Zuzarte

et al. 2014

Inf Syst Front

View full text Add to dashboard Cite

Progressive queries (PQ) are a new type of queries emerging from numerous contemporary database applications such as e-commerce, social network, business intelligence, and decision support. Such a PQ is formulated on the fly in several steps via a set of inter-related step-queries (SQ). In our previous work, we presented a framework to process a restricted type of PQs. However, how to process generic PQs remains an open problem. In this paper, we develop a novel technique to efficiently process generic PQs based on materialized views. The SQs of an in-process PQ can utilize the results of previous SQs not only from the same PQ but also from other in-process and completed PQs. The key idea is to create a multiple query dependency graph (MQDG), which captures the data source dependency relationships among SQs from multiple PQs. A mathematic model is developed to estimate the benefit of keeping the result of an SQ as a materialized view (critical SQ/node) based on the MQDG. The kept materialized views are used to improve the performance of the future SQs. Strategies for constructing the MQDG and identifying the critical SQs for materialization by using the MQDG are presented. To manage the storage of the materialized views, we introduce two approaches -one employs a greedy method and the other adopts a dynamic programming (DP) based method. Strategies are also suggested to reduce the input problem size for the DP procedure. Experimental results demonstrate that our technique is quite promising in efficiently processing PQs.

show abstract

A General Framework of Progressive Filtering and Its Application to Query by Singing/Humming

Cited by 42 publications

References 11 publications

Faster retrieval with a two-pass dynamic-time-warping lower bound

Faster retrieval with a two-pass dynamic-time-warping lower bound

M-MUSICS: an intelligent mobile music retrieval system

Optimization of generic progressive queries based on dependency analysis and materialized views

Contact Info

Product

Resources

About