This paper presents a framework for authoring, storing, retrieving, and presenting music lectures on the Web. For a synchronized presentation between score and recorded performance audio, we propose a dynamic programming-based algorithm for MIDI-to-Wave alignment to explore the temporal relations between MIDI and the corresponding performance recording. With rapid advances in music transcription technology, it had become more possible to align MIDI and wave in a symbolic domain. However, transcription errors usually occur when transcribing polyphonic music or multi-instruments music because the complex harmonic of different instruments. The proposed alignment algorithm works in the symbolic domain even if many transcription errors have occurred. The aligned MIDI and wave can be attached to many kinds of teaching materials. With a synchronized presentation, learners can read music scores and get instructional information when listening to certain sections of music pieces. We built an evaluation system for doing a subjective evaluation. The percentage of bars which were regarded as aligned perfectly and aligned within acceptable limits is 97.08%. The questionnaire in the evaluation system also reported positive opinions from both engineers and musicians.
[1]
Thomas Sikora,et al.
A Query by Humming System using MPEG-7 Descriptors
,
2004
.
[2]
Nicola Orio,et al.
Score Following Using Spectral Analysis and Hidden Markov Models
,
2001,
ICMC.
[3]
Ralf Steinmetz,et al.
Human Perception of Jitter and Media Synchronization
,
1996,
IEEE J. Sel. Areas Commun..
[4]
Nicola Orio,et al.
Alignment of Monophonic and Polyphonic Music to a Score
,
2001,
ICMC.
[5]
Ning Hu,et al.
Polyphonic Audio Matching for Score Following and Intelligent Audio Editors
,
2003,
ICMC.
[6]
Christopher Raphael,et al.
Automatic Segmentation of Acoustic Musical Signals Using Hidden Markov Models
,
1999,
IEEE Trans. Pattern Anal. Mach. Intell..