# Evaluating Loss Functions in Differentiable Out-of-Domain Sound-Matching with Partial Parameter Distance

arXiv: https://arxiv.org/abs/2608.27698 · HTML: https://mlsanity.com/paper/2608.27698/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [I'm Sorry for Your Loss: Spectrally-Based Audio Distances Are Bad at Pitch](https://mlsanity.com/paper/2012.04572/) (2020)
- [Sinusoidal Frequency Estimation by Gradient Descent](https://mlsanity.com/paper/2210.14476/) (2022)
- [InverSynth: Deep Estimation of Synthesizer Parameter Configurations from Audio Signals](https://mlsanity.com/paper/1812.06349/) (2018)
- [DawDreamer: Bridging the Gap Between Digital Audio Workstations and Python Interfaces](https://mlsanity.com/paper/2111.09931/) (2021)
- [Joint Time-Frequency Scattering for Audio Classification](https://mlsanity.com/paper/1512.02125/) (2015)
- [DiffMoog: a Differentiable Modular Synthesizer for Sound Matching](https://mlsanity.com/paper/2401.12570/) (2024)
- [The Shape of RemiXXXes to Come: Audio Texture Synthesis with Time-frequency Scattering](https://mlsanity.com/paper/1906.09334/) (2019)
- [Real-time Timbre Remapping with Differentiable DSP](https://mlsanity.com/paper/2407.04547/) (2024)
- [Mesostructures: Beyond Spectrogram Loss in Differentiable Time-Frequency Analysis](https://mlsanity.com/paper/2301.10183/) (2023)
- [Perceptual-Neural-Physical Sound Matching](https://mlsanity.com/paper/2301.02886/) (2023)
- [Evaluating Sound Similarity Metrics for Differentiable, Iterative Sound-Matching](https://mlsanity.com/paper/2506.22628/) (2025)

## Abstract (arXiv)

In out-of-domain (OOD) sound-matching, a synthesizer is optimized to mimic a sound it did not generate. OOD evaluation of loss functions is underexplored in part because the standard "parameter loss" metric requires a shared parameter space between target and imitator, which OOD settings lack. We introduce Partial Parameter Distance (PPD), which applies parameter loss only to the critical parameters that mismatched synthesizers share (e.g., filter cutoffs), enabling automatically evaluated OOD experiments; we verify its results with blinded listening tests. Across seven scenarios involving band-pass filtering, amplitude modulation, and pitch-bending, we evaluate four differentiable loss functions (SIMSE_Spec, L1_Spec, JTFS, DTW_Envelope). Loss-function effectiveness remains tightly coupled to the method of synthesis: SIMSE_Spec excels at filter-cutoff recovery, DTW_Envelope at amplitude-modulation recovery, and JTFS at smooth pitch trajectories. Parameter-based evaluation agrees with listening tests on the top-ranked loss function in five of seven scenarios, demonstrating its utility as a diagnostic tool.