Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.34533

STFT Frontend Mismatch in Pretrained Audio Spectrogram Transformers: Analysis and Adaptation

Julia Wilkins·Wei-Ching Lin·Abinaya Kumar·Shabnam Ghaffarzadegan·Juan Pablo Bellow
View original source ↗Read source document ↗Export metadata ↓

Abstract

Pretrained audio spectrogram transformers are widely used as backbones of machine listening systems for sound event classification. However, they are typically trained using spectrograms with a fixed Short-Time Fourier Transform (STFT) configuration, implicitly binding the model to the time-frequency resolution seen during pretraining. In practice, adapting these systems to new domains or computational constraints often requires different STFT frontend parameters. In this work, we conduct a controlled study of the sensitivity of the foundational Audio Spectrogram Transformer to variations in STFT window and hop size, showing that audio classification performance degrades substantially as frontend parameters deviate from pretraining settings. As a mitigation strategy, we introduce a lightweight conditioning mechanism using FiLM that enables a pretrained model to adapt to variable input configurations using limited additional training data. Our method generalizes well to unseen STFT configurations, improving model robustness without sacrificing performance in the original setting.

Explore related subjects

cs.SD

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Julia Wilkins, Wei-Ching Lin, Abinaya Kumar, Shabnam Ghaffarzadegan, Juan Pablo Bellow. 2026-10-25. STFT Frontend Mismatch in Pretrained Audio Spectrogram Transformers: Analysis and Adaptation. https://arxiv.org/abs/2610.34533

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

KEEP EXPLORING

Related papers

arXiv2026

Building a Dataset for Music Sample Identification

Sample identification (SI) is the task of matching an element of a musical work to its musically transformed versions used to create new works. The task has received little attention and lacks large-scale publicly available data. In this work, we mine sampling annotations from a music database and split them for training and evaluation. The resulting dataset is nearly three orders of magnitude larger than the existing SI benchmarks, with training, validation, and test sets of 114 k, 6 k, and 10 k tracks. We find that naively splitting the annotations places the same tracks in different sets. To avoid this, we construct a graph from the annotations and split it over connected components. We further find that a single mega-component contains half of the annotations, making component-wise splitting incompatible with balanced splits; we trim it, yielding a leakage-aware pipeline. We share the dataset for non-commercial scientific research purposes only and make the data-analysis and splitting code publicly available. We hope that our work fosters research on SI.

cs.SD↗
arXiv2026

RMS-AQA: A Two-Stage Spatial Audio Question Answering Benchmark for Real-World Domestic Environments

Embodied assistants in domestic environments must infer what happened, where and when it occurred, and how to respond. To address this, we introduce RMS-AQA, a spatial audio question answering (SAQA) benchmark for real-world domestic environments. The benchmark features a two-stage question-answering (QA) format to comprehensively assess the ability of audio-language models (ALMs) to first ground audible sound events and subsequently perform complex spatio-temporal reasoning based on that grounding. To maximize acoustic realism, our dataset combines authentic real-world first-order Ambisonics (FOA) recordings with high-fidelity synthetic data generated using measured room impulse responses (RIRs). Furthermore, we provide a lightweight spatial plug-in that injects FOA-format data into frozen audio-language backbones. Experimental results reveal that the primary challenges stem from concurrent sources, far distance, and sim-to-real domain gap between RIR-synthesized and authentic recordings.

cs.SD↗
arXiv2026

Commanding at the Speed of Sound: Audio-Centric Referring Expression Segmentation for Aerial Scenes

Referring expression segmentation (RES) aims to localize targets at the pixel level guided by human instructions. However, current models predominantly follow a text-centric paradigm that treats discrete text as the primary interaction medium for these human instructions. This assumption is especially limiting in unmanned aerial vehicle (UAV) applications, where rapid response, hands-free operation, and natural communication are often critical. In this paper, we reconstruct UAV referring expression segmentation through an audio-centric perspective. Grounded in information theory, we demonstrate that raw audio provides a higher upper bound for extracting rich semantic features than transcribed text. To achieve this, we construct an audio-driven UAV referring expression segmentation benchmark named Aerial-AudioRES by augmenting VisDrone with synthesized speech, forming "audio-text-image-mask" quadruples. Specifically, we employ an ambiguity filtering mechanism to ensure referential uniqueness, and incorporate eight distinct timbres alongside 4 realistic noises to simulate authentic environments. To drive the paradigm shift from text-centric to audio-centric, we propose the end-to-end Audio-centric Referring Expression Segmentation Network (ARES-Net). Distinct from discrete text-visual matching, our approach learns to establish a direct soft alignment between continuous acoustic manifolds and multi-scale visual representations. Comprehensive experiments show that our method obtains a peak accuracy of 64.23% in oIoU and demonstrates robust generalization on a collected real-human test set. Furthermore, it significantly reduces total interaction latency to one-third of the text-based method. Our code is available at https://github.com/LemonGauss/ARES-Net.

cs.SD↗