ACOUSTIC DOMAIN SHIFT IN SPOKEN LANGUAGE IDENTIFICATION FROM SYSTEMATIC DOMAIN GENERALIZATION EVALUATION TO REAL-WORLD APPLICATION
Abstract
Domain Generalization (DG) aims to develop models that remain robust to conditions unseen during training. While DG has been systematically studied in computer vision through controlled benchmarks and diverse distribution shifts, its evaluation in spoken language recognition remains less structured. Existing speech datasets provide valuable benchmarks for robustness to real-world acoustic conditions, but are primarily designed around specific scenarios and large scale rather than as general-purpose tools for systematically constructing and evaluating domain shifts. In this work, we introduce a smallscale speech dataset and evaluation protocol for controlled studies of acoustic domain shifts. It enables the evaluation of spoken language recognition models under a variety of acousitc domain shifts. We introduce the speech modality into the DomainBed Domain Generalization framework and evaluate three domain generalization algorithms. We show that in-domain performance is not a reliable predictor of cross-domain robustness and verify that explicit domain invariant algorithms such as MMD or DANN algorithms do not outperform ERM. We further validate the generality of these findings on MMS-LID-126, a state-of-the-art spoken language identification system. We release the code.
Related
- Linear and non-linear thermal system identification based on the integral of non-integer order — Application to solve inverse heat conduction linear and non-linear problems
- Petrov-Galerkin operator inference with application to stability-encouraging identification
- Power-posterior implicit sampling for efficient Bayesian experimental design: Application to contaminant source identification in groundwater flow
- Application of spectroscopic and multispectral imaging technologies on the assessment of ready-to-eat pineapple quality: A performance evaluation study of machine learning models generated from two commercial data analytics tools
- Roadmap for systematic identification and analysis of multiple biases in causal inference
BibTeX
@misc{derrida2026acoustic,
title = {{ACOUSTIC DOMAIN SHIFT IN SPOKEN LANGUAGE IDENTIFICATION FROM SYSTEMATIC DOMAIN GENERALIZATION EVALUATION TO REAL-WORLD APPLICATION}},
author = {Francois Derrida and Raphaël Duroselle and Thomas Courtat and Jean-François Bonastre},
howpublished = {HAL},
year = {2026},
month = sep,
url = {https://hal.science/hal-05759404v1},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - ACOUSTIC DOMAIN SHIFT IN SPOKEN LANGUAGE IDENTIFICATION FROM SYSTEMATIC DOMAIN GENERALIZATION EVALUATION TO REAL-WORLD APPLICATION
AU - Francois Derrida
AU - Raphaël Duroselle
AU - Thomas Courtat
AU - Jean-François Bonastre
PY - 2026
DA - 2026/09/23
PB - HAL
UR - https://hal.science/hal-05759404v1
AB - Domain Generalization (DG) aims to develop models that remain robust to conditions unseen during training. While DG has been systematically studied in computer vision through controlled benchmarks and diverse distribution shifts, its evaluation in spoken language recognition remains less structured. Existing speech datasets provide valuable benchmarks for robustness to real-world acoustic conditions, but are primarily designed around specific scenarios and large scale rather than as general-purpose tools for systematically constructing and evaluating domain shifts. In this work, we introduce a smallscale speech dataset and evaluation protocol for controlled studies of acoustic domain shifts. It enables the evaluation of spoken language recognition models under a variety of acousitc domain shifts. We introduce the speech modality into the DomainBed Domain Generalization framework and evaluate three domain generalization algorithms. We show that in-domain performance is not a reliable predictor of cross-domain robustness and verify that explicit domain invariant algorithms such as MMD or DANN algorithms do not outperform ERM. We further validate the generality of these findings on MMS-LID-126, a state-of-the-art spoken language identification system. We release the code.
ER -