Resumen:

In this study we compare the use of different music representations for retrieving alternative performances of the same musical piece, a task commonly referred to as version identification. Given the audio signal of a song, we compute descriptors representing its melody, bass line and harmonic progression using state-of-the-art algorithms. These descriptors are then employed to retrieve different versions of the same musical piece using a dynamic programming algorithm based on nonlinear time series analysis. First, we evaluate the accuracy obtained using individual descriptors, and then we examine whether performance can be improved by combining these music representations (i.e. descriptor fusion). Our results show that whilst harmony is the most reliable music representation for version identification, the melody and bass line representations also carry useful information for this task. Furthermore, we show that by combining these tonal representations we can increase version detection accuracy. Finally, we demonstrate how the proposed version identification method can be adapted for the task of query-by-humming. We propose a melody-based retrieval approach, and demonstrate how melody representations extracted from recordings of a cappella singing can be successfully used to retrieve the original song from a collection of polyphonic audio. The current limitations of the proposed approach are discussed in the context of version identification and query-by-humming, and possible solutions and future research directions are proposed.

• Marcado
• XML
• BibTex

PDFFile: 

salamon-mmir12.pdf

URL:

Resumen:

Content-based approaches to music retrieval are of great relevance as they do not require any kind of manually generated annotations. In this paper, we introduce the concept of structure fingerprints, which are compact descriptors of the musical structure of an audio recording. Given a recorded music performance, structure fingerprints facilitate the retrieval of other performances sharing the same underlying structure. Avoiding any explicit determination of musical structure, our fingerprints can be thought of a probability density function derived from a self-similarity matrix. We show that the proposed fingerprints can be compared using simple Euclidean distances without using any kind of complex warping operations required in previous approaches. Experiments on a collection of Chopin Mazurkas reveal that structure fingerprints facilitate robust and efficient content-based music retrieval. Furthermore, we give a musically informed discussion that also deepens the understanding of the popular Mazurka dataset.

• Marcado
• XML
• BibTex

PDFFile: 

055_ISMIR_2012.pdf

Palabras clave:

Resumen:

Time series are ubiquitous, and a measure to assess their similarity is a core part of many computational systems. Classical time series similarity measures based on dynamic time warping or the edit distance remain as the best general-purpose options, but their accuracies still leave much room for improvement. Here we propose a new approach to time series similarity based on the costs of iteratively jumping (or moving) between the sample values of two time series. We show that this approach can be very competitive when compared against the aforementioned classical measures. In fact, extensive experiments show that it can be statistically significantly superior for a number of data sources. Since the approach is also intuitive and computationally simple, we foresee its application as an alternative off-the-shelf tool to be used in time series retrieval, clustering, or classification systems.

• Marcado
• XML
• BibTex