A sound-based approach to video indexing and its application

Minami, Kenichi; Akutsu, Akihito; Hamada, Hiroshi; Tonomura, Yoshinobu

doi:10.1002/(sici)1520-684x(19981115)29:12<1::aid-scj1>3.0.co;2-3

Cited by 1 publication

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, we adopt a feature proposed by Minami et al that represents the intensity of the edge in the time direction of a sound spectrogram [7]. We call this feature the "spectral edge" in this study.…”

Section: Empirical Featuresmentioning

confidence: 99%

“…The first six features are based on the definition by Scheirer et al [9] and Tzanetakis et al [4], and the last one is based on that by Minami et al [7], with minor modifications.…”

Section: Empirical Featuresmentioning

confidence: 99%

“…They are based on empirical features such as edge intensity on a spectrogram [7] or the level of harmonicity [8]. They assume musical sounds comprising harmonic components with a stable frequency and are therefore not always effective.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A background music detection method based on robust feature extraction

Izumitani

Mukai

Kashino

2008

2008 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

We propose a music segment detection method for audio signals. Unlike many existing methods, ours specifically focuses on a background-music detection task, that is, detecting music used in background of main sounds. This task is important because music is almost always overlapped by speech or other environmental sounds in visual materials such as TV programs. Our method consists of feature extraction, dimension reduction, and statistical discrimination steps. For each step, we analyzed a set of methods to maximize the detection accuracy. With a simple post processing step, we achieved a framewise error rate as low as 8 % even when the mixed speech was louder than the target music by 10dB.Index Terms-Background music detection, Gaussian mixture model, k-nearest neighbor method, feature selection

show abstract

Section: Empirical Featuresmentioning

confidence: 99%

“…The first six features are based on the definition by Scheirer et al [9] and Tzanetakis et al [4], and the last one is based on that by Minami et al [7], with minor modifications.…”

Section: Empirical Featuresmentioning

confidence: 99%