Paper Archive

Estimating physical plate parameters from impulse responses is a challenging inverse problem. Task A of the first Digital Audio Effects Parameter Estimation Challenge requires the recovery of six identifiable parameters from displacement impulse responses. In this work, we propose a physics-inspired feature fusion network (PIFFN) that combines a pretrained convolutional backbone with a 15-dimensional physics-inspired feature vector computed from the impulse response. These physics-inspired features describe amplitude scale, temporal decay, and spectral structure without relying on modal-distribution priors. The proposed model is evaluated on the official validation set, achieving an overall normalized mean squared error of 0.00362. Compared with the official particle swarm optimization baseline and backbone-only model, PIFFN shows a clear performance improvement, demonstrating its effectiveness for plate parameter estimation.

Download

This paper presents SCAPES, a semantically conditioned autoregressive prior for environmental sound generation. The system models discrete audio representations using an autoregressive architecture conditioned on semantic information, enabling the generation of environmental sounds that follow user-specified concepts. By learning a prior over audio tokens, SCAPES combines high-level semantic control with detailed temporal modeling. Experimental evaluation investigates the quality, diversity, and semantic consistency of generated sounds, demonstrating the potential of autoregressive priors for controllable environmental sound synthesis.

Download

Deciding exactly when to move audio objects in immersive mixes is a labor-intensive artistic task. Current tools react strictly to instantaneous frequency overlaps, lacking the macroscopic awareness required for musically intentional spatial transitions. To model these decisions, we propose SEND (Spatial Event Neural Detector). Its dual-stream architecture analyzes the target track against its background context, combining a Spec-TNT backbone and a Temporal Convolutional Network (TCN) to capture hierarchical spectral features and precise rhythmic cues. Their dynamic interplay is modeled via a novel Cross-Track Gating Interaction (CTGI) mechanism.

Download

This paper presents our Task A submission to the 1st DAFx Parameter Estimation Challenge. We use the official ModalPlate dataset generator to synthesize 1000 one-second plate impulse responses with randomly sampled parameters inside the public ranges. A time-domain CNN-GRU regressor then estimates the six official Task A parameters from each unnormalised waveform. The model combines three one-dimensional convolutional blocks with a bidirectional gated recurrent unit and is trained with mean squared error on min-max normalised targets. The generated data are split into 700/150/150 train/validation/test examples, and the test split is never used during training or model selection. The implementation follows the official Task A format and exports evaluation-compatible prediction files for both development evaluation and blind-set submission.

Download

This demonstration presents Praat AudioTools, an open-source hybrid toolkit that repurposes Praat's phonetic-analysis environment for electroacoustic composition, sound design, and offline analysis–resynthesis workflows. Rather than treating analysis data as temporary measurements hidden inside an audio processor, Praat AudioTools exposes pitch contours, formant structures, temporal segmentations, spectral descriptors, phrase boundaries, stochastic trajectories, and host-application exchange files as editable compositional objects. These objects can be inspected, modified, chained, reused, and rendered into new sound transformations. The demonstration focuses on seven offline workflows: Neural Ambient Drone Designer, Praat for Max and Max for Live, Phase-Space Composer, Reich Generator, MCMC Musical Variation, Messagesquisse Opening, and Vector/Full-Chain composition workflows. None of the examples are presented as real-time effects. Instead, they show an "edit-in-the-middle" model in which sound is analyzed, intermediate representations are made visible, compositional decisions are applied to those representations, and the result is rendered as audio. The aim is to demonstrate a transparent alternative to both conventional black-box audio effects and end-to-end generative audio systems: a compositional environment where analysis objects become controllers, traces, scores, and reproducible technical artifacts.

Download

Given a target sound, finding the synthesizer preset that best reproduces it remains a core problem in sound design. Existing methods treat synthesis parameters as flat vectors, discarding the signal routing and parameter interactions that produce audio. We make two contributions. First, to learn a representation of parameters including their signal routing, we design a graph neural network whose message passing structure imitates FM signal processing. Second, we adapt the multimodal objective from SLAP to learn joint embeddings of audio and FM synthesizer parameters, enabling preset retrieval from a gallery. We focus on the Yamaha DX7, where six identical sinusoid operators interact according to one of 32 routing topologies. Our graph encoder's message passing weights are shared across all nodes and layers, enabling processing of arbitrary topologies of any size. When every topology is seen during training, the DX7-GNN and two baselines achieve strong audio-to-preset retrieval. When some topologies are held out for testing, the DX7-GNN substantially outperforms both baselines despite having the fewest parameters. Our ablations further support the claim that imitating FM signal flow in a parameter encoder improves generalization to unseen topologies.

Download

Automatic blind upmixing aims to convert audio from a smaller channel format (e.g. mono or stereo) into a multichannel format using estimates of direct and diffuse spatial statistics within the signal. Current approaches rely on primary-ambient extraction (PAE) algorithms, which lack real-world context through limited processing windows. Deep learning music source separation (MSS) models have been applied in voice-primary-ambient extraction (VPA) upmixing systems for handling direct components, but still rely on DSP methods of surround channel generation. This work further investigates utilizing source separation within VPA upmixing, focusing specifically on the task of stereo decorrelation and ambience extraction for 5.1 surround. We also release PAEDB (Primary–Ambient Extraction Dataset), a high-quality music dataset derived from MUSDB18-HQ and MoisesDB, comprising 1,809 primary–ambient stem pairs totaling over 550 hours of audio. The performance of selected DNNs trained on PAEDB is then evaluated using signal metrics and a listening study. Our findings indicate that DNNs can effectively model the behavior of PAE algorithms, establishing PAEDB as a strong foundation for ML upmixing systems and underscoring the need for higher-quality multichannel data to advance beyond conventional methods.

Download

We describe two submissions to Task B of the 1st DAFx Parameter Estimation Challenge, which estimates an unknown number of modal frequency, decay, and gain triples from a synthetic plate-reverb impulse response. The first method combines pooled spectral features with time-domain and absolute-scale conditioning in a real-valued convolutional count-density network, while the second uses a complex-valued Transformer count-density network. Both methods jointly infer the modal count and per-mode attributes directly from the IR. On an independently generated 100-IR comparison set, the two neural estimators achieve lower overall challenge error than the evaluated classical baselines, with frequency and decay estimation substantially more accurate than gain estimation.

Download

We present Clean2FX, a study and demo of label-conditioned clean-to-effect transformation for electric guitar audio. Given a clean guitar input and a target effect label, the task is to synthesize the corresponding effected signal while preserving the musical content. Training and evaluation pairs are constructed from EGFxSet real, single-tone recordings by assembling matched clean/effected chords, melodies, and mixed timelines. This allows for controlled comparison across effects. We evaluate four neural approaches under a common spectrogram-based transformation setting: two variational autoencoders and two U-Net models that differ in whether they operate on linear or log-magnitude representations. Performance is measured using linear-magnitude spectrogram MSE and Fréchet Audio Distance. The U-Net models outperform the variational autoencoder variants. Per-effect results show that distortion effects are most readily improved, whereas delay and reverb effects exhibit weaker FAD gains despite substantial spectral-error reductions. A conditioning-sensitivity diagnostic provides evidence that the best model responds to target labels rather than collapsing to a single transformation. Our demo website compares two models applied on real-world guitar performances outside training and validation data, providing audio and spectrogram examples of the practical clean-to-effect behavior.

Download

In this paper, we propose diffusion warm initialization as a simple yet effective approach for a range of audio-to-audio transformation tasks. To illustrate the generality of the approach, we demonstrate its use in timbre transfer, MIDI-to-Real synthesis, and multiple audio enhancement tasks. We conduct a detailed empirical analysis on timbre transfer to investigate the role of the initialization time t_init. The effect of t_init is evaluated using pitch-based Jaccard Distance and Fréchet Audio Distance to quantify faithfulness to the input signal and alignment with the target distribution. Our results provide practical guidance for selecting t_init and show that, once properly chosen, a single pretrained diffusion model combined with warm initialization can support multiple transformation objectives without task-specific training or conditioning. Despite its simplicity, this approach already achieves competitive results when compared with more complex pipelines designed specifically for these tasks.

Download