Publications

Project Publications

The Climate Change Smart Speakers: Probing Novel Vocal Imaginaries

By Søren Lyngsø Knudsen, Jonas Fritsch, Stina Marie Hasse Jørgensen, Ada Ada Ada
This paper introduces three climate-aware smart speakers—The Activist, The Voice of the Forest, and The Robot—designed to prompt users to consider climate change in their daily interactions. Each speaker employs a distinct voice and design, challenging the typical “assistant” role and engaging users as active participants in the climate discourse.

Listen to the AI-Generated Podcast Around it:

Cloning Voices and Making Kin: A Multivocal AI Approach to Kinship

By Ada Ada Ada, Stina Hasse Jørgensen, Jonas Fritsch

This work explores synthetic voice cloning as a tool for creating “kinship” through multivocal experiences. It provides a framework for using AI voice cloning in art and design, introducing three speculative prototypes—The Choral Voice, The Pooled Voice, and The Fluctuating Voice—that highlight multivocal synthetic voices as complex, interconnected entities​

Listen to the AI-Generated Podcast Around it:

Cultures of the AI Paralinguistic in Voice Cloning Tools

By Ada Ada Ada, Stina Hasse Jørgensen, Jonas Fritsch

This paper examines the paralinguistic capabilities of AI voice cloning tools, such as laughter and stuttering, and their potential to create new vocal cultures. Through experiments with ElevenLabs, the study discusses the tools’ limitations and the challenges of achieving expressive paralinguistic elements, raising questions on the embodied representations in synthetic voices.

Listen to the AI-Generated Podcast Around it:

MoSS: Unfolding Playful Imaginaries of Synthetic Voice Design through a Modular Smart Speaker

By: Søren Lyngsø Knudsen, Jonas Fritsch, Stina Hasse Jørgensen

MoSS (Modular Smart Speaker) is a prototype that combines smart speaker functions with modular synthesizer-like controls to explore new forms of synthetic vocality. By allowing real-time modifications to voice parameters, MoSS encourages users to engage with synthetic voices playfully and imaginatively, fostering novel vocal expressions and configurations​.

Listen to the AI-Generated Podcast Around it:

Voice as Infrastructure

By Marie Ertner, Stina Hasse Jørgensen, Signe L. Yndigeg

This audio paper investigates the concept of “voice as infrastructure,” likely discussing the foundational role of voice in digital and physical networks. It explores voice’s multifaceted implications in society, suggesting its role as a structuring element within technological ecosystems​.

Listen to it on soundcloud.

 

Past Publications

Johansen, S. S., van Berkel, N. and Fritsch, J. 2022. Characterising Soundscape Research in Human-Computer Interaction. In Designing Interactive Systems Conference (DIS ’22). Association for Computing Machinery, New York, NY, USA, 1394–1417. https://doi.org/10.1145/3532106.3533458

 
Fritsch, J. (2021): Problematizing Affective Interaction Design. In Affects, Interfaces, Events (eds: Thomsen, Kofoed & Fritsch), Imbricate! Press. 
 
Blichfeldt, M.E., Komang-Sønderbek, J., Højlund Westergård, F. & Fritsch, J.  (2018). The Living Tree; using Surface Transducers to explore the secret Life of Trees. Demo w. extended abstract in the Proceedings of Designing Interactive Systems (DIS)’18 Conference, Hong Kong, pp. 327-330.
 
Fritsch, J. & Jacobsen, M. (2017): The Voice Pump – an Affectively Engaging Interface for Changing Attachments.  In proceedings of DIS’17, Edinburgh, Scotland, pp. 265-269.
 

——

Stina Marie Hasse Jørgensen, Alice Emily Baird, Frederik Tollund Juutilainen, Mads Pelt & Nina Cecilie Højholdt. “The generation of a [multi’vocal] voice” in Seismograf Peer, special issue Sounds of Science: Composition, recording and listening as laboratory practice. Eds. Sanne Krogh Groth and Henrik Frisk. (2021).

Vasiliki Tsaknaki, Lena Kühn, Karin Ryding, Mai Hartmann, Maria Foverskov, Stina Jørgensen and Jonas Fritsch. “Breathing Commons: Affective and Somatic Relations Between Self and Others,” in 2021 Nordic Design Research Society (NORDES) conference (2021).

Stina Marie Hasse Jørgensen. Vocal Bodies: Performing Paralinguistic Stereotypes and Multivocalities in Art and Digital Media. PhD Dissertation, Department of Arts and Cultural Studies, University of Copenhagen, 2020.

Stina Marie Hasse Jørgensen, Alice Emily Baird, Frederik Tollund Juutilainen, Mads Pelt & Nina Cecilie Højholdt. “[multi’vocal]: Reflections on Engaging Everyday People in the Development of a Collective Non-Binary Synthesized Voice”, in EVA Copenhagen 2018 – Politics of the Machines – Art and After Conference Proceedings (2018).

Stina Marie Hasse Jørgensen.”ROBOT & THE END: A Comparative Critical Reading of the Staging of Synthesized Voices in Digital Media Performances,” in Peripeti Vol. 15 Nr. 29/30 (2018): Bodies of Difference/Kroppe I forskellighed. p.157-169.

Alice Emily Baird, Stina Hasse Jørgensen, Emilia Parada-Cabaleiro, Simone Hantke, Nicholas Cummins, and Bjorn Schuller “The Perception of Vocal Traits in Synthesized Voices: Age, Gender, and Human-Likeness,” in JAES. JAES, Audio Engineering Society, vol. 66 issue 4, pp. 277-285, (2018).

Stina Hasse Jørgensen, Sabrina Vitting-Seerup and Katrine Wallevik. “Hatsune Miku: An Uncertain Image,” in Digital Creativity, vol.28 issue 4, pp.318 – 331, (2017).

Alice Emily Baird, Stina Hasse Jørgensen, Emilia Parada-Cabaleiro, Simone Hantke, Nicholas Cummins, and Bjorn Schuller. “Perception of Paralinguistic Traits in Synthesized Voices,” in Proceedings from the 12th International Audio Mostly Conference. Co-written with (2017).