Content-based music retrieval using linear scaling and branch-and-bound tree search

Jang, Jyh-Shing Roger; Lee, Hong-Ru; Kao, Ming-Yang

doi:10.1109/icme.2001.1237713

Cited by 33 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, note extraction (or segmentation) is error-prone due to the continuity in pitch vectors obtained from human acoustic input. In viewing this disadvantage, the authors have also published their work (Chen & Jang, 1998;Lee, Jang, & Hsu, 1999;Jang, Chen, & Kao, 2001;Jang & Kao, 2000;Jang & Lee, 2001b;Jang, Lee, & Kao, 2001) on improving content-based music retrieval. The focus of Jang and Kao (2000) is on the use of dynamic programming techniques for elastic match in the comparison engine.…”

Section: Classification Of Mir Systemsmentioning

confidence: 94%

“…Jang and Lee (2001b) describes a music retrieval system ("query by tapping") based on beats only. Jang, Lee, and Kao (2001) proposed a MIRAI system that employs linear scaling for efficient nearest neighbor search. Jang and Lee (2001b) investigates a two-step hierarchical filtering method that can be optimized for MIRAI systems.…”

Section: Classification Of Mir Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Research and developments of a multi‐modal MIR engine for commercial applications in East Asia1

Jang

Lee

Chen

et al. 2004

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

This article describes the research and development of an efficient Music Information Retrieval (MIR) engine that is embedded in a karaoke software package targeted for Asian people's need of music retrieval. The MIR engine has a multi-modal interface that allows queries by singing, humming, tapping, speaking, and writing. In particular, we discuss the design philosophy, technical barriers, and performance evaluation of such an engine, as well as its current and potential commercial applications. Feedbacks and feature requests from users, which greatly influence our future work, are also addressed.

show abstract

Section: Classification Of Mir Systemsmentioning

confidence: 94%

Section: Classification Of Mir Systemsmentioning

confidence: 99%

Research and developments of a multi‐modal MIR engine for commercial applications in East Asia1

Jang

Lee

Chen

et al. 2004

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Recent studies on QBSH have used melody information as the only cue for retrieval [1]- [3], [7]. Ghias et al [1] proposed a query-by-humming method that involves using three characters (U, D, and S) to indicate whether the pitch of a note is higher than, lower than, or identical to the preceding note, and an approximate string-matching algorithm subsequently identifies Manuscript [2] enhanced the representation by considering rhythm information obtained from segmented notes.…”

Section: A Related Work: Melody and Textual Lyric Informationmentioning

confidence: 99%

Improving Query-by-Singing/Humming by Combining Melody and Lyric Information

Wang

Jang

2015

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

This paper proposes a novel method for improving query-by-singing/humming systems by using both melody and lyric information. First, singing/humming discrimination is performed to distinguish between singing and humming queries, which is achieved by considering the similarity between acoustic models. For the humming queries, a pitch-only melody recognition method that was ranked first among the MIREX (Music Information Retrieval Evaluation eXchange) query-by-singing/humming task submissions is applied. For the singing queries, a lyric similarity is computed using speech recognition techniques; the computed similarity is subsequently combined with the melody distance to exploit additional information in the lyrics. Several methods for combining melody distance and lyric similarity are investigated. Under the optimal experimental settings, the proposed query-by-singing/humming system achieves 51.19% error rate reduction for the top-10 retrieved results, indicating the feasibility of the proposed method.Index Terms-Combined melody distance and lyric similarity, query-by-singing/humming (QBSH), singing voice recognition, singing/humming discrimination (SHD).

show abstract

“…Jang in [7] presented a linear scaling method to cater for the humming speed variation issue. It uses 10 linear scaling variants from 0.75 to 1.25 for each reference melody candidate, which also means the size of the database is scaled up to 10 times.…”

Section: Introductionmentioning

confidence: 99%

“…Previous methods of music retrieval by humming are discrete music note-based approaches [1][2][3][4][5][6][7]. In the note-based approaches, a humming query is translated into a series of music notes.…”

Section: Introductionmentioning

confidence: 99%

Similarity matching of continuous melody contours for humming querying of melody databases

Zhu

Kankanhalli²,

Tian³

2002

2002 IEEE Workshop on Multimedia Signal Processing.

View full text Add to dashboard Cite

show abstract

Content-based music retrieval using linear scaling and branch-and-bound tree search

Cited by 33 publications

References 12 publications

Research and developments of a multi‐modal MIR engine for commercial applications in East Asia1

Research and developments of a multi‐modal MIR engine for commercial applications in East Asia1

Improving Query-by-Singing/Humming by Combining Melody and Lyric Information

Similarity matching of continuous melody contours for humming querying of melody databases

Contact Info

Product

Resources

About