01 / 01
Architecture buro



Shrinking voices at IRCAM Forum Workshops 2021

Mar , 15
Shrinking voices at IRCAM Forum Workshops 2021

19/03/2021, ore 13

Moderation: Hugues Vinet | Director of IRCAM’s R&D Department

Fabio Cifariello Ciardi
Shrinking voices
strategies and tools for the instrumental transcription of speech segments

In the past as well as today, the prosody of speech has spiked composers’ interest even when instrumental-only music is considered.  Today, however, despite the flourishing of increasingly effective audio-to-midi converters, scoring speech patterns for acoustic instruments still remains an elusive issue.
This is particularly the case when the original source is not concurrently audible and/or when the simple f0 tracking doesn’t satify composer’s needs.

Within this context, the presentation will illustrate a set of Open Music modules specifically tailored for the analysis and the compositional manipulation of prosodic descriptors. 
Using temporal and spectral information represented in the SDIF format, algorithms for pitch rectification (Mertens, & d’Alessandro, 1995), harmonicity-based segmentation (Parncutt & Strasburger,1994; MacCallum & Einbond, 2007) have been implemented together with several utilities for data filtering, clustering and quantization.
All modules share the same input-output data format to allow a smooth user interaction and feedback.

Although the speed of spectral changes in speech production exceeds both human and instrumental capabilities, the computer-assisted transcription of spoken voice is worth considering for at least two reasons.
Firstly, it places the prosodic features of speech at the roots of musical communication. Secondly, and on a more general note, it might contribute to further develop tools for the orchestration of dynamically changing spectra.

Orchestral and ensemble rendering of speech excerpts will be presented to outline the current state of the research.

Mertens, P. & Alessandro, Ch. d’ (1995) Pitch contour stylization using a tonal perception model. Proc. Int. Congr. Phonetic Sciences 13, 4, 228-231 (Stockholm 1995).
MacCallum, J., & Einbond, A. (2007, August). Real-time analysis of sensory dissonance. In International Symposium on Computer Music Modeling and Retrieval (pp. 203-211). Springer, Berlin, Heidelberg. Parncutt, R., & Strasburger, H. (1994). Applying psychoacoustics in composition:” harmonic” progressions of” nonharmonic” sonorities. Perspectives of new music, 88-129.

Transcription steps in Background checks for pre-recorded voice, video and orchestra (2019)

Subscribe to the newsletter

Edison Studio - Privacy policy © EdisonStudio 2020.
All Rights Reserved.