Recognition of Music Performances through Audio Matching

This paper reports a methodology for the identification of different music performances of the same music score. A statistical model of the possible performances of a given score is built from the recording of a single performance. To this end, the audio recording undergoes a segmentation process, followed by the extraction of the most relevant features of each segment. The model is built associating a state for each event and by modeling its emissions according to the computed features. The approach has been tested with a collection of orchestral music.

[1]  Freddy Y. Y. Choi.  Advances in domain independent linear text segmentation , 2000, ANLP.

[2]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[3]  Meinard Müller,et al.  Audio Matching via Chroma-Based Statistical Features , 2005, ISMIR.

[4]  Gerhard Widmer,et al.  MATCH: A Music Alignment Tool Chest , 2005, ISMIR.

[5]  George Tzanetakis,et al.  Polyphonic audio matching and alignment for music retrieval , 2003, 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684).

[6]  Nicola Orio.  Automatic Recognition of Audio Recordings , 2006, IRCDL.