Real Time Vowel Tremolo Detection Using Low Level Audio Descriptors
This work addresses a specific musical composition problem for composers, but it is incremental as it adapts existing techniques to a niche application.
The paper tackled the problem of extracting temporal structure from vowel tremolo in music by developing an interactive methodology using low-level MPEG7 audio descriptors and PCA for feature selection, aimed at enabling real-time detection in live creative contexts.
This paper resumes the results of a research conducted in a music production situation Therefore, it is more a final lab report, a prospective methodology then a scientific experience. The methodology we are presenting was developed as an answer to a musical problem raised by the Italian composer Marta Gentilucci. The problem was "how to extract a temporal structure from a vowel tremolo, on a tenuto (steady state) pitch." The musical goal was to apply, in a compositional context the vowel tremolo time structure on a tenuto pitch chord, as a transposition control.In this context we decide to follow, to explore the potential of low-level MPEG7 audio descriptors to build event detection functions. One of the main problems using low-level audio descriptors in audio analysis is the redundancy of information among them. We describe an "ad hoc" interactive methodology, based on side effect use of dimensionality reduction by PCA, to choose a feature from a set of low-level audio descriptors, to be used to detect a vowel tremolo rhythm. This methodology is supposed to be interactive and easy enough to be used in a live creative context.