Boosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards

• URL: http://arxiv.org/abs/2603.05231v1
• Date: Thu, 05 Mar 2026 14:43:15 GMT
• Title: Boosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards
• Authors: Linghan Fang, Tianxin Xie, Li Liu,
• Abstract summary: We present ASR-TRA, a novel Testtime Reinforcement Adaptation framework inspired by causal intervention.<n>Our method achieves higher accuracy while maintaining lower latency than existing TTA baselines.<n>Our approach provides a practical and robust solution for deploying ASR systems in challenging real-world conditions.
• Score: 8.109014000578766
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments and diverse accents. To address this issue, test-time adaptation (TTA) has shown great potential in improving the model adaptability at inference time without ground-truth labels, and existing TTA methods often rely on pseudo-labeling or entropy minimization. However, by treating model confidence as a learning signal, these methods may reinforce high-confidence errors, leading to confirmation bias that undermines adaptation. To overcome these limitations, we present ASR-TRA, a novel Test-time Reinforcement Adaptation framework inspired by causal intervention. More precisely, our method introduces a learnable decoder prompt and utilizes temperature-controlled stochastic decoding to generate diverse transcription candidates. These are scored by a reward model that measures audio-text semantic alignment, and the resulting feedback is used to update both model and prompt parameters via reinforcement learning. Comprehensive experiments on LibriSpeech with synthetic noise and L2 Arctic accented English datasets demonstrate that our method achieves higher accuracy while maintaining lower latency than existing TTA baselines. Ablation studies further confirm the effectiveness of combining audio and language-based rewards, highlighting our method's enhanced stability and interpretability. Overall, our approach provides a practical and robust solution for deploying ASR systems in challenging real-world conditions.

Related papers

• Training-Free Intelligibility-Guided Observation Addition for Noisy ASR [57.74127683005929]
  This paper proposes an intelligibility-guided observation addition (OA) method to improve speech recognition in noisy environments.<n>Experiments across diverse SE-ASR combinations and datasets demonstrate strong robustness and improvements over existing OA baselines.
  arXiv  Detail & Related papers  (2026-02-24T14:46:54Z)
• ASK: Adaptive Self-improving Knowledge Framework for Audio Text Retrieval [19.94287753279928]
  The dominant paradigm for Audio-Text Retrieval (ATR) relies on mini-batch-based contrastive learning.<n>The Gradient Locality Bottleneck (GLB) structurally prevents models from leveraging out-of-batch knowledge.<n>The Representation-Drift Mismatch (RDM) is where a static knowledge base becomes progressively misaligned with the evolving model, turning guidance into noise.
  arXiv  Detail & Related papers  (2025-12-11T14:48:30Z)
• Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation [60.04281435591454]
  CRDA (Curriculum Reinforcement-Learning Data Augmentation) is a novel framework guiding detectors to progressively master multi-domain forgery features.<n>Central to our approach is integrating reinforcement learning and causal inference.<n>Our method significantly improves detector generalizability, outperforming SOTA methods across multiple cross-domain datasets.
  arXiv  Detail & Related papers  (2025-11-10T12:45:52Z)
• Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders [50.52694757593443]
  Existing SAE training algorithms often lack rigorous mathematical guarantees and suffer from practical limitations.<n>We first propose a novel statistical framework for the feature recovery problem, which includes a new notion of feature identifiability.<n>We introduce a new SAE training algorithm based on bias adaptation'', a technique that adaptively adjusts neural network bias parameters to ensure appropriate activation sparsity.
  arXiv  Detail & Related papers  (2025-06-16T20:58:05Z)
• SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR [58.31068047426522]
  Test-Time Adaptation (TTA) aims to mitigate by adjusting models during inference.<n>Recent work explores combining TTA with external language models, using techniques like beam search rescoring or generative error correction.<n>We propose SUTA-LM, a simple yet effective extension of SUTA, with language model rescoring.<n> Experiments on 18 diverse ASR datasets show that SUTA-LM achieves robust results across a wide range of domains.
  arXiv  Detail & Related papers  (2025-06-10T02:50:20Z)
• A Novel Data Augmentation Approach for Automatic Speaking Assessment on Opinion Expressions [8.717610965852037]
  We propose a novel training paradigm to generate diverse responses of a given proficiency level.<n>We convert responses into synthesized speech via speaker-aware text-to-speech synthesis.<n>A multimodal large language model integrates aligned textual features with speech signals to predict proficiency scores directly.
  arXiv  Detail & Related papers  (2025-06-04T15:42:53Z)
• Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback [59.768119380109084]
  This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback.<n>We propose RiCL, a Reinforced interactive Continual Learning framework leveraging Large Language Models (LLMs)<n>Our RiCL approach substantially outperforms existing combinations of state-of-the-art online continual learning and noisy-label learning methods.
  arXiv  Detail & Related papers  (2025-05-15T03:22:03Z)
• Advancing Test-Time Adaptation in Wild Acoustic Test Settings [26.05732574338255]
  Speech signals follow short-term consistency, requiring specialized adaptation strategies. We propose a novel wild acoustic TTA method tailored for ASR fine-tuned acoustic foundation models. Our approach outperforms existing baselines under various wild acoustic test settings.
  arXiv  Detail & Related papers  (2023-10-14T06:22:08Z)
• Sequence-level self-learning with multiple hypotheses [53.04725240411895]
  We develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR) In contrast to conventional unsupervised learning approaches, we adopt the emphmulti-task learning (MTL) framework. Our experiment results show that our method can reduce the WER on the British speech data from 14.55% to 10.36% compared to the baseline model trained with the US English data only.
  arXiv  Detail & Related papers  (2021-12-10T20:47:58Z)
• An Approach to Improve Robustness of NLP Systems against ASR Errors [39.57253455717825]
  Speech-enabled systems typically first convert audio to text through an automatic speech recognition model and then feed the text to downstream natural language processing modules. The errors of the ASR system can seriously downgrade the performance of the NLP modules. Previous work has shown it is effective to employ data augmentation methods to solve this problem by injecting ASR noise during the training process.
  arXiv  Detail & Related papers  (2021-03-25T05:15:43Z)

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.