Creating and Controlling Synthetic Voices

May 13th, 2016 10:00 am 
Steim, Achtergracht 19, 1017WL, Amsterdam Steim, Achtergracht 19, 1017WL, Amsterdam

There are many different ways to produce an artificial voice on the computer, from knitting every single sinusoidal sound of it, to transform pre-recorded speech and singing samples, and now even going to the cloud and tap into online speech synthesis web services.

Screen Shot 2016-03-13 at 17.25.50 (2)
DATE: 13th of May, 2016
TIME: 10:00 – 13:00
COST: €25
– send a mail to tijs [at] steim [dot] nl
– maximum of 12 participants
LOCATION: STEIM, Achtergracht 19, 1017WL, Amsterdam

In this workshop, Nicolas d’Alessandro will approach the creation of synthetic voices in two ways. First we will put our hands into actually making vocal sounds in Max and/or Pure Data, browsing the 4-5 most common synthesis techniques. Then we will discuss and demonstrate how to control vocal sounds in performance. Voice is not an easy medium to “make sound good”, so we will explore how the choice of the controllers and the gestures can affect our ability to get where we expect with artificial voice synthesis.
– Participants should bring their own laptop with Max or Pure Data (Pd) installed.
– A basic knowledge of patching with these programs is required.
this workshop is part of The Art of Voice Synthesis
conference, expert meeting, workshop, concert
11 – 12 – 13 May 2016, Amsterdam
University of Amsterdam & Orgelpark & STEIM
Synthetic speech is part of modern everyday life. Artificial voices do not only occur in multifaceted technological uses, but they also feed back into researching the natural human voice. Moreover, artists, musicians and composers find a source of inspiration in the artificial sound of such voices. Our conference inquires both the richness of the human voice and the limits and surplus of its theoretical modelling and mechanical and digital imitation. We are specifically interested in modelling and synthesizing so-called “extended vocal techniques” – all sounds the human voice can produce, exceeding conventional singing and speaking. The conference will cover the history of the artificial voice, extended vocal techniques, aspects of theoretical modelling and technical realization, and the role of the artificial voice in contemporary music. Academics, scientists and artists will come together to exchange ideas and insights in three days of presentations, meetings, workshops and a concert. With a group of international experts we will place the artificial voice in a broad perspective of historical, technical, socio-cultural, artistic and musical investigation.

About the instructor


Sonic Dreams Festival, Soma Contemporary Gallery, Waterford, Ireland, 25-26 September 2015

Sonic Dreams Festival, Soma Contemporary Gallery, Waterford, Ireland, 25-26 September 2015

Nicolas d’Alessandro obtained his PhD in Applied Sciences from the University of Mons in 2009. From a lifelong interest in musical instruments and his acquired taste in speech and singing processing, he will incrementally shape a research topic that aims at using gestural control of sound in order to gain insights in speech and singing production. Late 2009, he moves to Canada, to take a postdoc position with Prof. Sidney Fels at the MAGIC Lab, University of British Columbia, Vancouver, where he will work on the DiVA project. Since early 2015, he has left academia and founded Hovertone, a startup standing at the crossing between arts and technology.