Music retrieval by humming-using similarity retrieval over high dimensional feature vector space

Kosugi, Naoko; Nishihara, Yuichi; Kon'ya, Seiichi; Yamamuro, Masashi; Kushima, Kazuhiko

doi:10.1109/pacrim.1999.799561

Cited by 17 publications

(11 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several metadata based searching techniques are made like vector space model, Boolean model, indexing, invert index file, cosine measure etc [6] [7] [8] [9]. Currently storing of exact metadata is being more emphasized as per to the standards of Web 2.0.…”

Section: Litrature Reviewmentioning

confidence: 99%

Hybrid Query by Humming and Metadata Search System (HQMS) Analysis over Diverse Features

Khan¹,

Mushtaq²

2011

IJACSA

View full text Add to dashboard Cite

Abstract-Retrieval of music content over web is one of the toughest job tasks and found some of the significant challenge. Song retrieval over web is the emerging problem from the category of Music Information Retrieval. Several searching techniques related to metadata and content of song are developed and implemented. In this paper we are going to propose and evaluate a new hybrid technique for song retrieval named as "hybrid query by humming and metadata search system" (HQMS).HQMS is a hybrid model that is based on metadata and query by humming. HQMS narrow downs the relevant results thus improve overall accuracy of the system. Two filters, metadata and query by humming work together and enhances overall accuracy. The system is evaluated song wise, metadata wise and Age wise. Issues related to query reformulation are also highlighted as a part of the paper. More over the evaluation validates the hypothesis and the proposed Architecture.

show abstract

Section: Litrature Reviewmentioning

confidence: 99%

Hybrid Query by Humming and Metadata Search System (HQMS) Analysis over Diverse Features

Khan¹,

Mushtaq²

2011

IJACSA

View full text Add to dashboard Cite

show abstract

“…Most research that uses monophonic musical information has as its source of data a collection of folk songs [8,22,24,26], or a small collection of melodies [15]. A variety of techniques have been used to locate melodic matches, including dynamic programming [22,23], n-gram-based matching [9], feature histograms [17], and state matching [22].…”

Section: Other Mir Projectsmentioning

confidence: 99%

An architecture for effective music information retrieval

Uitdenbogerd¹,

Zobel²

2004

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

We have explored methods for music information retrieval for polyphonic music stored in the MIDI format. These methods use a query, expressed as a series of notes that are intended to represent a melody or theme, to identify similar pieces. Our work has shown that a three-phase architecture is appropriate for this task, in which the first phase is melody extraction, the second is standardisation, and the third is query-to-melody matching. We have investigated and systematically compared algorithms for each of these phases. To ensure that our results are robust, we have applied methodologies that are derived from text information retrieval: we developed test collections and compared different ways of acquiring test queries and relevance judgements. In this paper we review this program of work, compare to other approaches to music information retrieval, and identify outstanding issues.

show abstract

“…In [4], a new approximate string matching algorithm is proposed to match feature strings, such as melody strings, rhythm strings, and chord strings, of music objects in a music database. Kosugi et al [5] described a retrieval system that enables a user to obtain the name of a desired song from an audio database by humming a part of a melody as a query. A music information retrieval system dealing with MIDI files using complex-valued recurrent neural networks is proposed in [6].…”

Section: Introductionmentioning

confidence: 99%

Content-based audio classification and retrieval using a fuzzy logic system: towards multimedia search engines

Liu

Wan

Wang

2002

Soft Computing - A Fusion of Foundations, Methodologies and App

View full text Add to dashboard Cite

In recent years, available audio corpora are rapidly increasing from fast growing Internet and digital libraries. How to classify and retrieve sound files relevant to the user's interest from large databases is crucial for building multimedia web search engines. In this paper, content-based technology has been applied to classify and retrieve audio clips using a fuzzy logic system, which is intuitive due to the fuzzy nature of human perception of audio, especially audio clips with mixed types. Two features selected from various extracted features are used as input to a constructed fuzzy inference system (FIS). The outputs of the FIS are two types of hierarchical audio classes. The membership functions and rules are derived from the distributions of extracted audio features. Speech and music can thus be discriminated by the FIS. Furthermore, female and male speech can be separated by another FIS, whereas percussion can be distinguished from other music instruments. In addition, we can use multiple FISs to form a ''fuzzy tree'' for retrieval of more types of audio clips. With this approach, we can classify and retrieve generic audios more accurately, using fewer features and less computation time, compared to other existing approaches.

show abstract

Music retrieval by humming-using similarity retrieval over high dimensional feature vector space

Cited by 17 publications

References 5 publications

Hybrid Query by Humming and Metadata Search System (HQMS) Analysis over Diverse Features

Hybrid Query by Humming and Metadata Search System (HQMS) Analysis over Diverse Features

An architecture for effective music information retrieval

Content-based audio classification and retrieval using a fuzzy logic system: towards multimedia search engines

Contact Info

Product

Resources

About