Download Audio Visualization via Delay Embedding and Subspace Learning We describe a sequence of methods for producing videos from audio signals. Our visualizations capture perceptual features like harmonicity and brightness: they produce stable images from periodic sounds and slowly-evolving images from inharmonic ones; they associate jagged shapes to brighter sounds and rounded shapes to darker ones. We interpret our methods as adaptive FIR filterbanks and show how, for larger values of the complexity parameters, we can perform accurate frequency detection without the Fourier transform. Attached to the paper is a code repository containing the Jupyter notebook used to generate the images and videos cited. We also provide code for a realtime C++ implementation of the simplest visualization method. We discuss the mathematical theory of our methods in the two appendices.
Download Unsupervised Text-to-Sound Mapping via Embedding Space Alignment This work focuses on developing an artistic tool that performs an
unsupervised mapping between text and sound, converting an input text string into a series of sounds from a given sound corpus.
With the use of a pre-trained sound embedding model and a separate, pre-trained text embedding model, the goal is to find a mapping between the two feature spaces. Our approach is unsupervised which allows any sound corpus to be used with the system.
The tool performs the task of text-to-sound retrieval, creating a
soundfile in which each word in the text input is mapped to a single sound in the corpus, and the resulting sounds are concatenated
to play sequentially. We experiment with three different mapping
methods, and perform quantitative and qualitative evaluations on
the outputs. Our results demonstrate the potential of unsupervised
methods for creative applications in text-to-sound mapping.
Download Evaluating Tokenization Strategies for Expressive Classical Piano Performance Generation Expressive piano performance generation needs symbolic pitch, timing, and dynamics. We evaluate six tokenization strategies for a Transformer that generates classical piano performances. Our tokenizations add velocity, beat annotations, and sustain pedal, from note-only to full representations. We pretrain on MAESTRO, then finetune on ASAP with beat-level annotations. The model uses anticipatory-style note encoding with cross-attention on composer and genre. FAD on the ASAP test set shows that note + velocity + pedal and full modes achieve the lowest mean FAD (1.76 and 1.97). Both beat the note-only baseline (3.10). Beat tokens show mixed, category-dependent effects and do not improve the best modes on average.
Download InstructFX2FX: A Multi-Turn Text-to-Effect System for Sequential Audio Effect Refinement We present InstructFX2FX, a system for sequential audio effect refinement through multi-turn natural-language instructions. Existing text-to-effect systems are largely single-shot, mapping one textual descriptor to one preset. Real audio engineering is instead sequential: engineers refine an existing effect chain through successive instructions. This poses a stateful problem that single-shot systems do not address: given the current effect parameters state and a new instruction, update the sound while preserving what earlier instructions already achieved. InstructFX2FX addresses this with a hybrid architecture that divides labor between a language model and CLAP-guided optimization. The LLM serves as a high-level planner that selects effects and proposes the initial parameter state, motivated by recent evidence that LLMs can outperform CLAP-based optimization for single-turn text-to-effect mapping; CLAP-guided optimization then refines the existing parameter state, providing a more stable and robust refinement mechanism than LLM reprompting. In the demo, attendees drive a dry recording through successive natural-language instructions: after each turn, they choose how strongly the effect is applied, then issue the next instruction based on what still differs from the sound they intend. In a preliminary evaluation on SocialFX-derived descriptor pairs, CLAP-guided refinement achieves lower DSP-feature MMD than an LLM+LLM initialize-then-reprompt baseline on 9 of 10 pairs. Trajectory analysis further shows that, for differentiable effects, optimization tends to gradually move the audio toward the new target while retaining the effects of the previous instruction, highlighting the potential for gradual refinement. Audio demo and source code are available online.