Content-based music structure analysis with applications to music semantics understanding

Maddage, Namunu C.; Xu, Changsheng; Kankanhalli, Mohan; Shao, Xi

doi:10.1145/1027527.1027549

Cited by 79 publications

(47 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…piano keys) within one octave, but all octaves are folded together. The idea of calculating harmonic features over beat-length segments appears to have been developed several times; we first became aware of it in [10].…”

Section: Chroma Featuresmentioning

confidence: 99%

Identifying `Cover Songs' with Chroma Features and Dynamic Programming Beat Tracking

Ellis

Poliner

2007

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07

226

213

View full text Add to dashboard Cite

Large music collections, ranging from thousands to millions of tracks, are unsuited to manual searching, motivating the development of automatic search methods. When different musicians perform the same underlying song or piece, these are known as 'cover' versions. We describe a system that attempts to identify such a relationship between music audio recordings. To overcome variability in tempo, we use beat tracking to describe each piece with one feature vector per beat. To deal with variation in instrumentation, we use 12-dimensional 'chroma' feature vectors that collect spectral energy supporting each semitone of the octave. To compare two recordings, we simply cross-correlate the entire beat-by-chroma representation for two tracks and look for sharp peaks indicating good local alignment between the pieces. Evaluation on several databases indicate good performance, including best performance on an independent international evaluation, where the system achieved a mean reciprocal ranking of 0.49 for true cover versions among top-10 returns.

show abstract

Section: Chroma Featuresmentioning

confidence: 99%

Identifying `Cover Songs' with Chroma Features and Dynamic Programming Beat Tracking

Ellis

Poliner

2007

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07

226

213

View full text Add to dashboard Cite

show abstract

“…HMMs have also been proven suitable for the closely related task of key detection (Lee and Slaney, 2007;Noland and Sandler, 2006). The context information about the key of the piece can be exploited as a third option for smoothing chord predictions (Maddage et al, 2004;Shenoy and Wang, 2005). An approach that integrates bass pitch estimation in a probabilistic framework for hypothesis-search-based chord recognition is described by Sumi et al (2008).…”

Section: Context-sensitive Chord and Key Recognitionmentioning

confidence: 99%

Adaptive music retrieval–a state of the art

Stober

Nürnberger

2012

Multimed Tools Appl

View full text Add to dashboard Cite

With the development of more and more sophisticated Music Information Retrieval (MIR) approaches, aspects of adaptivity are becoming an increasingly important research topic. Even though, adaptive techniques have already found their way into MIR systems and contribute to robustness or user satisfaction they are not always identified as such. This paper attempts a structured view on the last decade of MIR research from the perspective of adaptivity in order to increase awareness and promote the application and further development of adaptive techniques. To this end, different approaches from a wide range of application areas that share the common aspect of adaptivity are identified and systematically categorized.

show abstract

“…Maddage et al (2004) describe a system in which a partial transcription is used to make decisions about structure, integrating beat tracking, rhythm extraction, chord detection and melodic similarity in a heuristic framework for detecting all segments in a song. They also propose using octave-scale rather than Mel-frequency scale cepstral coefficients as pitch-oriented representation.…”

Section: Segmentation By Rhythm and Pitchmentioning

confidence: 99%

Using duration models to reduce fragmentation in audio segmentation

et al. 2006

View full text Add to dashboard Cite

We investigate explicit segment duration models in addressing the problem of fragmentation in musical audio segmentation. The resulting probabilistic models are optimised using Markov Chain Monte Carlo methods; in particular, we introduce a modification to Wolff's algorithm to make it applicable to a segment classification model with an arbitrary duration prior. We apply this to a collection of pop songs, and show experimentally that the generated segmentations suffer much less from fragmentation than those produced by segmentation algorithms based on clustering, and are closer to an expert listener's annotations, as evaluated by two different performance measures.

show abstract

Content-based music structure analysis with applications to music semantics understanding

Cited by 79 publications

References 9 publications

Identifying `Cover Songs' with Chroma Features and Dynamic Programming Beat Tracking

Identifying `Cover Songs' with Chroma Features and Dynamic Programming Beat Tracking

Adaptive music retrieval–a state of the art

Using duration models to reduce fragmentation in audio segmentation

Contact Info

Product

Resources

About