Towards Microphone-Invariant Speech Representations for Transformer-Based Voice Disorder Detection

Automatic voice disorder detection from speech offers strong potential for early diagnosis and continuous disease monitoring. While models based on pre-trained transformers have improved detection performance, their robustness to microphone variation remains underexplored, particularly for consumer-grade devices. To the best of our knowledge, we present the first study of microphone mismatch in transformer-based binary voice disorder detection across 20 smartphone microphones. While most mismatched microphone conditions cause moderate performance degradation, the worst-case condition reduces unweighted average recall by up to 12.53 percentage points. To address this, we introduce a Barlow Twins-inspired module to learn microphone-invariant representations. Our approach reduces the performance gap between matched and mismatched conditions by up to 62%, while maintaining comparable matched-condition performance. Qualitative analysis of the embedding space demonstrates more compact, distinct speaker clusters across microphones. Importantly, results indicate generalisation to unseen microphones across manufacturers, smartphone generations, and release periods, without requiring any inference-time adaptation.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.21140
Primary Topic
Voice and Speech Disorders
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Towards Microphone-Invariant Speech Representations for Transformer-Based Voice Disorder Detection

Felix Putze, Marvin Borsdorf, Tanja Schultz, Iva Ewert
arXiv (Cornell University)
Voice and Speech Disorders
preprint

Towards Microphone-Invariant Speech Representations for Transformer-Based Voice Disorder Detection

Felix Putze, Marvin Borsdorf, Tanja Schultz, Iva Ewert
preprint en

Abstract

Automatic voice disorder detection from speech offers strong potential for early diagnosis and continuous disease monitoring. While models based on pre-trained transformers have improved detection performance, their robustness to microphone variation remains underexplored, particularly for consumer-grade devices. To the best of our knowledge, we present the first study of microphone mismatch in transformer-based binary voice disorder detection across 20 smartphone microphones. While most mismatched microphone conditions cause moderate performance degradation, the worst-case condition reduces unweighted average recall by up to 12.53 percentage points. To address this, we introduce a Barlow Twins-inspired module to learn microphone-invariant representations. Our approach reduces the performance gap between matched and mismatched conditions by up to 62%, while maintaining comparable matched-condition performance. Qualitative analysis of the embedding space demonstrates more compact, distinct speaker clusters across microphones. Importantly, results indicate generalisation to unseen microphones across manufacturers, smartphone generations, and release periods, without requiring any inference-time adaptation.

arXiv (Cornell University)
Voice and Speech Disorders
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon