Navigating the Reality Gap: Privacy-Preserving Adaptation of ASR for Challenging Low-Resource Domains

• URL: http://arxiv.org/abs/2512.16401v2
• Date: Mon, 22 Dec 2025 16:22:23 GMT
• Title: Navigating the Reality Gap: Privacy-Preserving Adaptation of ASR for Challenging Low-Resource Domains
• Abstract summary: We show that a robust multilingual model (IndicWav2Vec) degrades to a 40.94% WER on rural clinical data from India, rendering it unusable.<n>To address this, we explore a zero-data-exfiltration framework enabling localized, continual adaptation via Low-Rank Adaptation (LoRA)<n>Our results demonstrate that multi-domain Experience Replay (ER) yields the primary performance gains, achieving a 17.1% relative improvement in target WER and reducing catastrophic forgetting by 55% compared to naive adaptation.
• Score: 4.585227671447896
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic Speech Recognition (ASR) holds immense potential to assist in clinical documentation and patient report generation, particularly in resource-constrained regions. However, deployment is currently hindered by a technical deadlock: a severe "Reality Gap" between laboratory performance and noisy, real-world clinical audio, coupled with strict privacy and resource constraints. We quantify this gap, showing that a robust multilingual model (IndicWav2Vec) degrades to a 40.94% WER on rural clinical data from India, rendering it unusable. To address this, we explore a zero-data-exfiltration framework enabling localized, continual adaptation via Low-Rank Adaptation (LoRA). We conduct a rigorous investigative study of continual learning strategies, characterizing the trade-offs between data-driven and parameter-driven stability. Our results demonstrate that multi-domain Experience Replay (ER) yields the primary performance gains, achieving a 17.1% relative improvement in target WER and reducing catastrophic forgetting by 55% compared to naive adaptation. Furthermore, we observed that standard Elastic Weight Consolidation (EWC) faced numerical stability challenges when applied to LoRA in noisy environments. Our experiments show that a stabilized, linearized formulation effectively controls gradient magnitudes and enables stable convergence. Finally, we verify via a domain-specific spot check that acoustic adaptation is a fundamental prerequisite for usability which cannot be bypassed by language models alone.

Related papers

• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• CRISP: Constrained Refinement via Iterative Squeezing Process for Robust Medical Image Segmentation under Domain Shift [7.9644155369405665]
  "Rank Stability of Positive Regions" is a working assumption under distribution shift.<n>We propose CRISP, a model-agnostic framework that requires no test-time parameter updates and no target-domain data.<n>We show that CRISP significantly outperforms state-of-the-art methods with striking HD95 reductions of up to 0.14.
  arXiv  Detail & Related papers  (2026-07-16T17:32:26Z)
• Recovering Clinical Utility Under Differential Privacy: Empirical Validation of Adaptive Federated Aggregation on Heterogeneous Cardiovascular Datasets [0.06372261626436676]
  The present work addresses the gap by validating the FedCVR framework on five publicly available real cardiovascular datasets.<n>Results demonstrate that FedCVR preserves its adaptive advantage on real data, achieving an F1-Score of 79.2% and AUC of 0.96.<n>The measured privacy cost on real data confirms the graceful degradation pattern observed in the synthetic experiments.
  arXiv  Detail & Related papers  (2026-07-07T18:51:13Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• CRISP: Rank-Guided Iterative Squeezing for Robust Medical Image Segmentation under Domain Shift [7.9644155369405665]
  We introduce Rank Stability of Positive Regions'', which states that the relative rank of predicted probabilities for positive voxels remains stable under distribution shift.<n>We then design an iterative training framework, making HP and HR progressively squeeze'' to the final segmentation.<n>CRISP is the first framework to make segmentation based on rank rather than probabilities.
  arXiv  Detail & Related papers  (2026-04-07T04:05:36Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems [53.52419750390942]
  Large language models (LLMs) are used in mission-critical factual domains.<n>LLMs exhibit poor calibration performance due to noisy retrieved contexts.<n>We propose NAACL Rules (Noise-AwAre Confidence CaLibration Rules) to provide a principled foundation for resolving overconfidence under noise.
  arXiv  Detail & Related papers  (2026-01-16T05:38:25Z)
• Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection [62.89126207012712]
  Face Presentation Attack Detection (PAD) demands incremental learning to combat spoofing tactics and domains.<n>Privacy regulations forbid retaining past data, necessitating rehearsal-free learning (RF-IL)
  arXiv  Detail & Related papers  (2025-12-22T04:30:11Z)
• SG-OIF: A Stability-Guided Online Influence Framework for Reliable Vision Data [6.4391040754741296]
  In this paper, we introduce a Stability-Guided Online Influence Framework (SG-OIF) for Approximating training-point influence on test predictions.<n>We show that SG-OIF achieves 91.1% accuracy in the top 1% prediction samples on the CIFAR-10, and 99.8% AUPR score on MNIST.
  arXiv  Detail & Related papers  (2025-11-21T19:58:54Z)
• Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty [48.593888815135934]
  Large Language Models (LLMs) are increasingly important for safe deployment in high-stakes domains.<n>Existing recovery methods rely on data-intensive global parameter adjustments, implicitly assuming that SFT deeply corrupts the models' ability to recognize their knowledge boundaries.<n>We propose Honesty-Critical Neurons Restoration (HCNR) to surgically repair this suppressed capacity.
  arXiv  Detail & Related papers  (2025-11-17T05:30:48Z)
• Constrained Adversarial Perturbation [16.05659740749269]
  Universal Adversarial Perturbations (UAPs) have emerged as a powerful tool for both stress testing model robustness and scalable adversarial training.<n>We propose Constrained Adversarial Perturbation (CAP), an efficient algorithm that solves this problem using a gradient based alternating optimization strategy.
  arXiv  Detail & Related papers  (2025-10-17T14:44:20Z)
• Bridging the Synthetic-Real Gap: Supervised Domain Adaptation for Robust Spacecraft 6-DoF Pose Estimation [13.83897333268682]
  Spacecraft Pose Estimation is a fundamental capability for autonomous space operations such as rendezvous, docking, and in-orbit docking.<n>Existing domain adaptation approaches aim to mitigate this issue but often underperform when a modest number of labeled target samples are available.<n>We propose the first Supervised Domain Adaptation (SDA) framework tailored for SPE keypoint regression.
  arXiv  Detail & Related papers  (2025-09-17T08:03:05Z)
• Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift [12.373281238541296]
  Medical vision-language models (VLMs) offer promise for clinical decision support, yet their reliability under distribution shifts remains a major concern for safe deployment.<n>We propose DRiFt, a structured feature decoupling framework that explicitly separates clinically relevant signals from task-agnostic noise.<n>Our approach improves in-distribution performance by +11.4% Top-1 accuracy and +3.3% Macro-F1 over prior prompt-based methods.
  arXiv  Detail & Related papers  (2025-09-11T12:26:57Z)
• Inference Gap in Domain Expertise and Machine Intelligence in Named Entity Recognition: Creation of and Insights from a Substance Use-related Dataset [6.343399421398501]
  Nonmedical opioid use is an urgent public health challenge.<n>We present a named entity recognition (NER) framework to extract two categories of self-reported consequences from social media narratives.<n>We evaluate both fine-tuned encoder-based models and state-of-the-art large language models (LLMs) under zero- and few-shot in-context learning settings.
  arXiv  Detail & Related papers  (2025-08-26T23:09:43Z)
• A Contrastive Learning-Guided Confident Meta-learning for Zero Shot Anomaly Detection [17.73056562717683]
  CoZAD is a novel zero-shot anomaly detection framework.<n>It integrates soft confident learning with meta-learning and contrastive feature representation.<n>We show it outperforms existing methods on 6 out of 7 industrial benchmarks.
  arXiv  Detail & Related papers  (2025-08-25T09:27:31Z)
• An Uncertainty-guided Tiered Self-training Framework for Active Source-free Domain Adaptation in Prostate Segmentation [10.061310311839856]
  Source-free Domain Adaptation (SFDA) is a promising technique to adapt deep segmentation models to address privacy and security concerns. We propose a novel Uncertainty-guided Tiered Self-training (UGTST) framework to achieve stable domain adaptation.
  arXiv  Detail & Related papers  (2024-07-03T08:13:16Z)
• Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation [91.83820250747935]
  Pseudo-label noise is mainly contained in unstable samples in which predictions of most pixels undergo significant variations during self-training. We introduce the Stable Neighbor Denoising (SND) approach, which effectively discovers highly correlated stable and unstable samples. SND consistently outperforms state-of-the-art methods in various SFUDA semantic segmentation settings.
  arXiv  Detail & Related papers  (2024-06-10T21:44:52Z)
• Practically adaptable CPABE based Health-Records sharing framework [0.0]
  We have suggested a CPABE and OAuth2.0 based framework for efficient access-control and authorization respectively to improve the practicality of EHR sharing across a single client-application. Our implementation of the suggested framework along with its analytical comparison signifies its potential in terms of efficient performance and minimal latency.
  arXiv  Detail & Related papers  (2024-03-11T00:23:17Z)
• Cloud-based Federated Learning Framework for MRI Segmentation [0.10878040851637999]
  This paper proposes a novel framework tailored for brain tissue segmentation in rural healthcare facilities. The framework employs a deep reinforcement learning environment in tandem with a refinement model (RM) deployed locally at rural healthcare sites. We demonstrate the efficacy of our approach by training the network with a limited data set and observing a substantial performance enhancement.
  arXiv  Detail & Related papers  (2024-03-01T03:39:17Z)
• PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection [65.24854366973794]
  Node-level graph anomaly detection (GAD) plays a critical role in identifying anomalous nodes from graph-structured data in domains such as medicine, social networks, and e-commerce. We introduce a simple method termed PREprocessing and Matching (PREM for short) to improve the efficiency of GAD. Our approach streamlines GAD, reducing time and memory consumption while maintaining powerful anomaly detection capabilities.
  arXiv  Detail & Related papers  (2023-10-18T02:59:57Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer [60.31021888394358]
  Unsupervised Domain Adaptation (UDA) can effectively address domain gap issues in real-world image Super-Resolution (SR) We propose a SOurce-free Domain Adaptation framework for image SR (SODA-SR) to address this issue, i.e., adapt a source-trained model to a target domain with only unlabeled target data.
  arXiv  Detail & Related papers  (2023-03-31T03:14:44Z)
• Towards Lifelong Learning of End-to-end ASR [81.15661413476221]
  Lifelong learning aims to enable a machine to sequentially learn new tasks from new datasets describing the changing real world without forgetting the previously learned knowledge. An overall relative reduction of 28.7% in WER was achieved compared to the fine-tuning baseline when sequentially learning on three very different benchmark corpora.
  arXiv  Detail & Related papers  (2021-04-04T13:48:53Z)
• Privacy Preserving Recalibration under Domain Shift [119.21243107946555]
  We introduce a framework that abstracts out the properties of recalibration problems under differential privacy constraints. We also design a novel recalibration algorithm, accuracy temperature scaling, that outperforms prior work on private datasets.
  arXiv  Detail & Related papers  (2020-08-21T18:43:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.