Download Towards Morphological Sound Description using segmental models
We present an approach to model the temporal evolution of audio descriptors using Segmental Models (SMs). This method yields a signal segmentation into a sequence of primitives, constituted by a set of user-defined trajectories . This allows one to consider specific primitive shapes, model their duration and to take into account the time dependence between successive signal frames, contrary to standard Hidden Markov Models. We applied this approach to a database of violin playing. Various types of glissando and dynamics variations were specifically recorded. The results show that our approach using Segmental Models provides a segmentation that can be easily interpreted. Quantitatively, the Segmental Models performed better than standard implementation of Hidden Markov Models.
Download Score based real-time performance with a virtual violin
This paper describes the implementation of a violin physical model tied with the control of music scores to enable the real-time performance of music pieces. The violin model is made of four strings, which allows the performance of double stops, chords and specific resonant effects that can be encountered in violin playing. A graphic tablet is used to control the bowing parameters and to trigger automatically note events contained in a specifically formatted MIDI file. The automatic pitch change helps reducing the violin playing complexity and enables the user to focus on sound shaping and phrasing. The device can be used for pure sound synthesis purposes as well as for experiments related to violinists’ sound control. However, the simplified interface for sound and score events is particularly suitable for non violinists wishing to explore expressive capabilities of the instrument and to experience specific features of violin playing.