varia.website/content/2022/remnants-of-future-voices-EN.md

39 lines
5.2 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

Title: Remnants of Future Voices
Date: 2022-12-10
Category: workshops
Tags: voices, speech-synthesis, machine-learning
Slug: remnants-of-future-voices
lang: en
event_start: 2022-12-10 12:00
event_duration: 5h
featured_image: /images/radios to a doppelganger.png
summary: In this workshop we will explore ancestral cosmology through the figure of the clone in artificial voice technologies. The workshop will experiment with artistic approaches to future and past-oriented dialogues using voice avatars of ourselves and others, considering the implications of creating a clone that may speak to generations beyond our own lifetime and say things we have never said.
**Date**: Saturday, 10 December 2022<br>
**Time**: 12:00-17:00 (CEST) including lunch <br>
**Location**: Varia (Gouwstraat 3, Rotterdam)
**Registration Link**: [register here](https://forms.gle/sHwTcJbiPqC76JQv6)
*"When we walk upon Mother Earth, we always plant our feet carefully because we know the faces of our future generations are looking up at us from beneath the ground."* Chief Oren Lyons, address to the United Nations (1992)
*"its easy to mistake distance for unreality, to treat the limits of what we can see as the limits of the world. But just as the world does not stop at our doorstep or our countrys borders, neither does it stop with our generation, or the next."* William MacAskill, What we Owe the Future (2022)
*"Ive dreamed of looking into a mirror and seeing my alter ego which, on its own initiative, begins to tell me unbearable truths."* Joanna Russ, The Female Man (1975)
In this workshop we will explore ancestral cosmology through the figure of the clone in artificial voice technologies. The workshop will experiment with artistic approaches to future and past-oriented dialogues using voice avatars of ourselves and others, considering the implications of creating a clone that may speak to generations beyond our own lifetime and say things we have never said.
*Data. Memory. Prediction.* What traces of our living selves remain within machine learnings? What aspects of identity would we want to preserve, or do we choose to allow our clones to take on a completely different identity? How do we encode wishes and messages that exceed both our temporary bodies and recorded data? How do we populate a data+algorithmic memory space with remnants to carry forward and be appropriated - to be ancestors, as opposed to ghosts?
Everyone attending the workshop will be asked to consider their own relationship to an open concept of ancestry, and how they relate to the ideas and actions of those having lived and those yet to be. These reflections will take form through a series of small artistic contributions developed through the workshop. The artistic contributions are part of a process of collaboratively building datasets which are used to train the machine learning models of the artificial BroadCaster in the year-long radio broadcast **>>In Search of Good Ancestors / Ahnen in Arbeit<<** [http://ahnen.in](http://ahnen.in) whose voices are shaped by learning the nuances of human and non-human recorded utterances.
The workshop will be led by **Jonathan Chaim Reus** in collaboration with **Angeliki Diakrousi** from Varia, a collective infrastructure who have been developing artistic approaches for reading, annotating, speaking and listening together across different open source softwares.
==============================================
**>>In Search of Good Ancestors / Ahnen in Arbeit<<** is a year-long experiment in generative radio by Jonathan Chaim Reus, investigating the nature of datasets and machine learning algorithms as unstable, intergenerational memory. A 24-hour broadcast on German Public Radio features the voice(s) of an artificial BroadCaster, a bespoke generative voice instrument utilizing deep learning text and speech models that begin pre-trained on widely used public research datasets. The BroadCaster mutates via trainings on small-scale datasets created collaboratively through a series of public workshops.
The Broadcast + Workshops navigates themes of long-term and intergenerational thinking - using as its seminal text American virologist Jonas Salks 1977 lecture "Are we being good ancestors?". Here, Salk, a renowned altruist, calls for the cultures of "the West" to make intergenerational responsibility the highest moral imperative. Through the year the BroadCaster repeatedly attempts to extrapolate on this lecture, its predictions altered by the contributions of texts, stylistic annotations and voice recordings collected in the workshops. Thus, new vocal identities and poetic styles emerge in excess of the single voice, while those of the initial trainings decay over time through a process of "catastrophic forgetting" when being trained on a dataset whose diversity unfolds over time.
The broadcast streams from January 2022 - February 2023 at ahnen.in, while fragments are played intermittently on German Public Radio until end of December 2022. The workshops activities were conceived in collaboration with artist-researcher Eleni Ikoniadou, and Angeliki Diakrousi, Joana Chicau, amy pickles and Cristina Cochior of VARIA. This work is commissioned by CTM Festival, Deutschlandfunk Kultur and ORF Ö1 Kunstradio, with additional support from the Leverhulme Trust.