Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 1610.02475

A Music-generating System Inspired by the Science of Complex Adaptive Systems

Shawn Bell·Liane Gabora
View original source ↗Read source document ↗Export metadata ↓

Abstract

This paper presents NetWorks (NW), an interactive music generation system that uses a hierarchically clustered scale free network to generate music that ranges from orderly to chaotic. NW was inspired by the Honing Theory of creativity, according to which human-like creativity hinges on (1) the ability to self-organize and maintain dynamics at the 'edge of chaos' using something akin to 'psychological entropy', and (2) the capacity to shift between analytic and associative processing modes. At the 'edge of chaos', NW generates patterns that exhibit emergent complexity through coherent development at low, mid, and high levels of musical organization, and often suggests goal seeking behaviour. The architecture consists of four 16-node modules: one each for pitch, velocity, duration, and entry delay. The Core allows users to define how nodes are connected, and rules that determine when and how nodes respond to their inputs. The Mapping Layer allows users to map node output values to MIDI data that is routed to software instruments in a digital audio workstation. By shifting between bottom-up and top-down NW shifts between analytic and associative processing modes.

Explore related subjects

cs.SDnlin.AOq-bio.NC

Keep this discovery

BibTeXRIS

Shawn Bell, Liane Gabora. 2016-10-08. A Music-generating System Inspired by the Science of Complex Adaptive Systems. https://arxiv.org/abs/1610.02475

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗