Content-Based Music Retrieval Using Beat Information

Islam, Mohammad Khairul; Lee, Hyungjin; Paul, Anjan Kumar; Baek, Joong-Hwan

doi:10.1109/fskd.2007.227

Cited by 5 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In smoothing, the data points of a signal are modified so that individual points that are higher than the immediately adjacent points are reduced, and points that are lower than the adjacent points are increased [18]. This, naturally, represents a smoother signal.…”

Section: Smoothingmentioning

confidence: 98%

“…If there is analogous one, then we extract them from database, and we find the exact location of that query music in the database using peak period matching method. According to [18], we get only one main beat if the length of query music is too short so that, we just compare that beat with the database. But if the query is large, then we can get more than one beat, and we compare the beats in order with the database.…”

Section: Music Matchingmentioning

confidence: 99%

“…Depending on the situation, beat may denote either the onset of the corresponding time unit, a point in time, the very moment when the metronome ticks, or the complete time interval between two consecutive taps [18]. According to the energy, two types of beats are considered such as strong and weak beats.…”

Section: Feature Extractionmentioning

confidence: 99%

“…As referenced by [18], we use the probability of τ in some music with a view to extract the main beat. Since, strong and weak beats in music appear repeatedly, we describe the energy using the following equation:…”

Section: Figure 2 (B) Energy Peak Pointmentioning

confidence: 99%

“…Our matching method consists of two parts as referenced [18]. Firstly, we look for the query song using main beat and the peak periods.…”

Section: Music Matchingmentioning

confidence: 99%

See 4 more Smart Citations

An Efficient Music Retrieval Using Noise Cancellation

Parvin¹,

Park²

2007

Future Generation Communication and Networking (FGCN 2007)

View full text Add to dashboard Cite

In this paper we present a music retrieval method. The algorithm works in two steps: noise cancellation and music retrieval. In noise cancellation step we apply filtering on psychoacoustic representation of the given music signal to get a clean noise-free signal which can truly represent the music. Each music has a particular and unique beat pattern called main beat. This representative feature from the noise-free signal is extracted which is followed by one matching method at the retrieval stage. Similar types of features are extracted from the music database or training music as well as the test music. For feature extraction, a music signal is primarily segmented into small windows in the time domain. Extracted features from both the training and query music are matched using similarity matching algorithm. 94% retrieval accuracy of our method is quiet satisfactory. Our experimental result shows the feasibility of our approach.

show abstract

Section: Smoothingmentioning

confidence: 98%

Section: Music Matchingmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

Section: Figure 2 (B) Energy Peak Pointmentioning

confidence: 99%

“…Our matching method consists of two parts as referenced [18]. Firstly, we look for the query song using main beat and the peak periods.…”

Section: Music Matchingmentioning

confidence: 99%