Search papers, labs, and topics across Lattice.
The paper introduces Texture Resonance Retrieval (TRR), a novel audio representation based on Gram matrices of Wav2Vec2 activations, for retrieval-grounded audio effect control. TRR aims to bridge the semantic gap between user intent and low-level DSP parameters by retrieving editable plugin configurations. Evaluated on a guitar-effects benchmark, TRR demonstrates superior performance in minimizing normalized parameter error compared to CLAP and other retrieval baselines, validated through ablation studies and a listening test.
Forget tweaking knobs – this new Gram-matrix-based audio representation lets you *retrieve* the perfect, editable audio effect preset, outperforming standard methods.
Digital audio workstations expose rich effect chains, yet a semantic gap remains between perceptual user intent and low-level signal-processing parameters. We study retrieval-grounded audio effect control, where the output is an editable plugin configuration rather than a finalized waveform. Our focus is Texture Resonance Retrieval (TRR), an audio representation built from Gram matrices of projected mid-level Wav2Vec2 activations. This design preserves texture-relevant co-activation structure. We evaluate TRR on a guitar-effects benchmark with 1,063 candidate presets and 204 queries. The evaluation follows Protocol-A, a cross-validation scheme that prevents train-test leakage. We compare TRR against CLAP and internal retrieval baselines (Wav2Vec-RAG, Text-RAG, FeatureNN-RAG), using min-max normalized metrics grounded in physical DSP parameter ranges. Ablation studies validate TRR's core design choices: projection dimensionality, layer selection, and projection type. A near-duplicate sensitivity analysis confirms that results are robust to trivial knowledge-base matches. TRR achieves the lowest normalized parameter error among evaluated methods. A multiple-stimulus listening study with 26 participants provides complementary perceptual evidence. We interpret these results as benchmark evidence that texture-aware retrieval is useful for editable audio effect control, while broader personalization and real-audio robustness claims remain outside the verified evidence presented here.