Bj?rn Thor J¨®nsson

• J¨®nsson, Bj?rn Thor; Erdem, Cagri; Fasciani, Stefano & Glette, Kyrre (2024). Cultivating Open-Earedness with Sound Objects discovered by Open-Ended Evolutionary Systems. I Grace, Kazjon; Llano, Maria Teresa; Martins, Pedro & Hedblom, Maria (Red.), Proceedings of the Fifteenth International Conference on Computational Creativity. Association for Computational Creativity (ACC). ISSN 978-989-54160-6-6. s. 381¨C386. Fulltekst i vitenarkiv
• J¨®nsson, Bj?rn Thor; Erdem, Cagri & Glette, Kyrre (2024). A System for Sonic Explorations With Evolutionary Algorithms. Journal of The Audio Engineering Society. ISSN 1549-4950. 72(4), s. 257¨C266. doi: 10.17743/jaes.2022.0137.
• J¨®nsson, Bj?rn Thor; Erdem, Cagri; Fasciani, Stefano & Glette, Kyrre (2024). Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs. I Johnson, Colin; Rebelo, S¨¦rgio M. & Santos, Iria (Red.), Artificial Intelligence in Music, Sound, Art and Design. Springer Nature. ISSN 9783031569920. doi: 10.1007/978-3-031-56992-0_14. Fulltekst i vitenarkiv

Se alle arbeider i Cristin

• J¨®nsson, Bj?rn Th¨®r (2025). Demonstration of phylogenetic explorer and sequencer.
• J¨®nsson, Bj?rn Thor (2025). Facilitating serendipitous sound discoveries with simulations of open-ended evolution.
• J¨®nsson, Bj?rn Th¨®r (2025). Extended Data for: Quality-Diversity Search in Sound Generation: Investigating Innovation Engines for Audio Exploration. Vis sammendrag

  Data accompanying the article Quality-Diversity Search in Sound Generation: Investigating Innovation Engines for Audio Exploration. The Innovation Engine algorithm is used to evolve sounds, where Quality Diversity search is guided by the YAMNet classifier to discover sounds. (2024-08-15) This study draws on the challenges that composers and sound designers face in creating and refining new tools to achieve their musical goals. Utilising evolution- ary processes to promote diversity and foster serendipitous discoveries, we propose to automate the search through uncharted sonic spaces for sound discovery. We argue that such diversity promoting algorithms can bridge a technological gap between the theoretical realisation and practical accessibility of sounds. Specif- ically, in this paper we describe a system for generative sound synthesis using a combination of Quality Diversity (QD) algorithms and a supervised discrimi- native model, inspired by the Innovation Engine algorithm. The study explores different configurations of the generative system and investigates the interplay between the chosen sound synthesis approach and the discriminative model. We further examine the interaction between Compositional Pattern Producing Net- works (CPPNs) and Digital Signal Processing (DSP) graphs, introducing a novel approach with multiple specialized CPPNs for different frequency ranges. This configuration results in simpler CPPN networks while maintaining comparable performance to single-CPPN setups. The research also investigates evolution- ary stepping stones by analyzing goal switches between musical and non-musical contexts, revealing how lineages traverse unlikely paths to current elites. Addi- tionally, we explore the temporal dimension of sound generation by expanding the behavior space from a previous study to include various sound durations, uncovering specialization within temporal niches. The results indicate that a combination of CPPN + Digital Signal Processing (DSP) graphs coupled with Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) and a deep learn- ing classifier can generate a substantial variety of synthetic sounds. Our expanded experiments demonstrate the system¡¯s ability to produce diverse and innovative sound objects across different temporal and contextual dimensions. The study concludes by presenting the generated sound objects through an online explorer and as rendered sound files. Furthermore, in the context of music composition, we present an experimental application that showcases the creative potential of our discovered sounds, highlighting the system¡¯s capacity for generating versatile sonic material across various durations and contexts. (2024-08-15)

• J¨®nsson, Bj?rn Th¨®r (2025). Supporting data for: Exploring Definitions of Quality and Diversity in Sonic Measurement Spaces. Vis sammendrag

  Data accompanying the article Exploring Definitions of Quality and Diversity in Sonic Measurement Spaces The Innovation Engine algorithm is used to evolve sounds, where Quality Diversity search is guided by Behaviour Definitions by unsupervised models and full-reference and no-reference quality evaluation approaches. (2025-01-17) Sonic discoveries have shaped and transformed creative processes in sound art and music production. Compositions prompted by new timbres influence and improve our lives. Modern technology offers a vast space of sonic possibilities to explore. Background and expertise influence the explorers ability to navigate that space of possibilities. Efforts have been made to develop automated systems that can systematically generate and explore these sonic possibilities. One route of such efforts has involved the search for diversity and quality with evolutionary algorithms, automating the evaluation of those metrics with supervised models. We continue on that path of investigation by further exploring possible definitions of quality and diversity in sonic measurement spaces by applying and dynamically redefining unsupervised models to autonomously illuminate sonic search spaces. In particular we investigate the applicability of unsupervised dimensionality reduction models for defining dynamically expanding, structured containers for a quality diversity search algorithm to operate within. Furthermore we evaluate different approaches for defining sonic characteristics with different feature extraction approaches. Results demonstrate considerable ability in autonomously discovering a diversity of sounds, as well as limitations of simulating evolution within the confines of a single, structured, albeit dynamically redefined, search landscape. Sound objects discovered in traversals through such autonomously illuminated sonic spaces can serve as resources in shaping our lives and steering them through diverse creative paths, along which stepping stones towards interesting innovations can be collected and used as input to human culture. (2025-01-17)

• J¨®nsson, Bj?rn Th¨®r (2024). Supporting Data for: Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs. Vis sammendrag

  Data accompanying the article Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs. The Innovation Engine algorithm is used to evolve sounds, where Quality Diversity search is guided by the YAMNet classifier to discover sounds. (2023-11-07) This study proposes the application of a system for generative sound synthesis that automates the discovery of inspiring sounds using Quality Diversity algorithms and a discriminative model inspired by the Innovation Engine algorithm. The approach addresses the challenges composers face in creating and refining new tools to achieve their musical goals. By promoting diversity and fostering serendipitous discoveries, the proposed approach expands the composer¡¯s palette and makes the entirety of the sonic domain more accessible. The study presents generated sound objects through an online explorer and as rendered sound files, as well as an experimental application showcasing the creative potential of the discovered sounds. Our proposed approach offers a promising direction for sonic design that embraces automation, serendipity, and creativity. (2023-11-08)

• J¨®nsson, Bj?rn Th¨®r (2024). Phytobenthos 1. Vis sammendrag

  A playlist of livestream recordings during several nights of stochastic sequencing through sets of sounds found during runs with different configurations of quality diversity search.

• J¨®nsson, Bj?rn Th¨®r; Erdem, Cagri; Fasciani, Stefano & Glette, Kyrre (2024). Cultivating Open-Earedness with Sound Objects discovered by Open-Ended Evolutionary Systems. Vis sammendrag

  Interaction with generative systems can face the choice of generalising towards a middle ground or diverging towards novelty. Efforts have been made in the domain of sounds to enable divergent exploration in search of interesting discoveries. Those efforts have been confined by pre-trained models and single environments. We are building on those efforts to enable autonomous discovery of sonic landscapes. Furthermore, we draw inspiration from research on open-ended evolution to continuously provide evolutionary processes with new opportunities for sonic discoveries. Exposure to autonomously discovered sound objects can elevate openness to sonic experiences, which in turn offers inspiring opportunities for creative work involving sounds.

• J¨®nsson, Bj?rn Th¨®r; Erdem, ?a?ri; Fasciani, Stefano & Glette, Kyrre (2024). Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs. Vis sammendrag

  This study draws on the challenges that composers and sound designers face in creating and refining new tools to achieve their musical goals. Utilising evolutionary processes to promote diversity and foster serendipitous discoveries, we propose to automate the search through uncharted sonic spaces for sound discovery. We argue that such diversity promoting algorithms can bridge a technological gap between the theoretical realisation and practical accessibility of sounds. Specifically, in this paper we describe a system for generative sound synthesis using a combination of Quality Diversity (QD) algorithms and a discriminative model, inspired by the Innovation Engine algorithm. The study explores different configurations of the generative system and investigates the interplay between the chosen sound synthesis approach and the discriminative model. The results indicate that a combination of Compositional Pattern Producing Network (CPPN) + Digital Signal Processing (DSP) graphs coupled with Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) and a deep learning classifier can generate a substantial variety of synthetic sounds. The study concludes by presenting the generated sound objects through an online explorer and as rendered sound files. Furthermore, in the context of music composition, we present an experimental application that showcases the creative potential of our discovered sounds.

• J¨®nsson, Bj?rn Th¨®r (2023). Live Rendering and -Coding Evolved Sounds.
• J¨®nsson, Bj?rn Th¨®r (2023). Jukebox with research data. Vis sammendrag

  Evolution runs explorer: opening up access to current results from the application of quality diversity search algorithms to the discovery of synthesised sounds. https://synth.is/exploring-evoruns

• J¨®nsson, Bj?rn Th¨®r (2023). kromosynth CLI. Vis sammendrag

  A command line interface to kromosynth and gRPC service.

• J¨®nsson, Bj?rn Th¨®r (2023). kromosynth. Vis sammendrag

  Sonic design with evolutionary algorithms: The engine behind synth.is and kromosynth-cli for audio waveform breeding with neuro-evolution of pattern producing networks and quality diversity search.

• J¨®nsson, Bj?rn Th¨®r (2023). Live Streams From Evolutionary Search for Sounds. Vis sammendrag

  Here we present a web interface for navigating sounds discovered during runs of evolutionary processes. Those runs are performed as a part of investigations into the applicability of quality diversity search for sounds. This audible peek into the collected data supplements statistical analysis. Such a way of communicating the current results is intended to provide an engaging experience of the data. By either listening to automatic playback of the discovered sounds, or interacting with them, for example by changing their parameters, interesting, annoying, pleasing, and perhaps useful artefacts may be discovered, modified and downloaded for use in any creative work. The application can be accessed from desktops or mobile devices at: https: //synth.is/exploring-evoruns

• J¨®nsson, Bj?rn Thor (2022). Embodiment of audio evolution.
• J¨®nsson, Bj?rn Th¨®r; Hoover, Amy K. & Risi, Sebastian (2015). Interactively Evolving Compositional Sound Synthesis Networks. Vis sammendrag

  While the success of electronic music often relies on the uniqueness and quality of selected timbres, many musicians struggle with complicated and expensive equipment and techniques to create their desired sounds. Instead, this paper presents a technique for producing novel timbres that are evolved by the musician through interactive evolutionary computation. Each timbre is produced by an oscillator, which is represented by a special type of artificial neural network (ANN) called a compositional pattern producing network (CPPN). While traditional ANNs compute only sigmoid functions at their hidden nodes, CPPNs can theoretically compute any function and can build on those present in traditional synthesizers (e.g. square, sawtooth, triangle, and sine waves functions) to produce completely novel timbres. Evolved with NeuroEvolution of Augmenting Topologies (NEAT), the aim of this paper is to explore the space of potential sounds that can be generated through such compositional sound synthesis networks (CSSNs). To study the effect of evolution on subjective appreciation, participants in a listener study ranked evolved timbres by personal preference, resulting in preferences skewed toward the first and last generations. In the long run, the CSSN¡¯s ability to generate a variety of different and rich timbre opens up the intriguing possibility of evolving a complete CSSN-encoded synthesizer.

Se alle arbeider i Cristin