Contrastive Regularization for Accent-Robust ASR

• URL: http://arxiv.org/abs/2605.03297v1
• Date: Tue, 05 May 2026 02:35:44 GMT
• Title: Contrastive Regularization for Accent-Robust ASR
• Abstract summary: We investigate supervised contrastive learning (SupCon) as a lightweight, accent-invariant auxiliary objective for CTC fine-tuning.<n>SupCon provides an effective and model-agnostic regularization strategy for improving accent robustness.
• Score: 5.302303646066551
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: ASR systems based on self-supervised acoustic pretraining and CTC fine-tuning achieve strong performance on native speech but remain sensitive to accent variability. We investigate supervised contrastive learning (SupCon) as a lightweight, accent-invariant auxiliary objective for CTC fine-tuning. An utterance-level contrastive loss regularizes encoder representations without architectural modification or explicit accent supervision. Experiments on the L2-ARCTIC benchmark show consistent WER reductions across multiple pretrained encoders, with up to 25 -- 29\% relative reduction under unseen-accent evaluation. Analysis using within-transcript cosine dispersion indicates that SupCon promotes more compact and stable representation geometry under accent variability. Overall, SupCon provides an effective and model-agnostic regularization strategy for improving accent robustness.

Related papers

• Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition [50.15288513086986]
  Contrastive decoding (CD) originally introduced to stabilize large language model (LLM)-based audio-visual speech recognition (AVSR) systems.<n>We propose reliability-aware scaling of CD for AVSR.
  arXiv  Detail & Related papers  (2026-08-26T08:25:15Z)
• Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition [5.310289270050359]
  Dynamic-Adaptive Contrastive Learning (DyCo-CL) is a geometry-aware framework that couples Virtual Adrialversa Augmentation (VAA) with a semantic consistency loss.<n>DyCo-CL achieves a 6.27% accuracy gain in 1-shot settings over prior methods.
  arXiv  Detail & Related papers  (2026-05-26T06:33:57Z)
• 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)
• Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition [61.39209522608919]
  Unified Speech Recognition has emerged as a semi-supervised framework for training a single model for audio, visual, and audiovisual speech recognition.<n>We propose CTC-driven teacher forcing, where greedily decoded CTC pseudo-labels are fed into the decoder to generate attention targets.<n>Because CTC and CTC-driven attention pseudo-labels have the same length, the decoder can predict both simultaneously.
  arXiv  Detail & Related papers  (2026-02-22T19:38:21Z)
• Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition [21.893229843453458]
  We introduce Moe-Ctc, a Mixture-of-Experts architecture with intermediate CTC supervision that jointly promotes expert specialization and generalization.<n>During training, accent-aware routing encourages experts to capture accent-specific patterns, which gradually transitions to label-free routing for inference.<n>Experiments on the Mcv-Accent benchmark demonstrate consistent gains across both seen and unseen accents in low- and high-resource conditions, achieving up to 29.3% relative WER reduction over strong FastConformer baselines.
  arXiv  Detail & Related papers  (2026-02-02T11:16:34Z)
• Listen, Attend, Understand: a Regularization Technique for Stable E2E Speech Translation Training on High Variance labels [0.49109372384514843]
  Listen, Attend, Understand (LAU) is a semantic regularization technique that constrains the acoustic encoder's latent space during training.<n>We evaluate our method on a Bambara-to-French dataset with 30 hours of Bambara speech translated by non-professionals.
  arXiv  Detail & Related papers  (2026-01-03T08:45:59Z)
• New Insights into Optimal Alignment of Acoustic and Linguistic Representations for Knowledge Transfer in ASR [30.00166986946003]
  We take a new insight to regard alignment and matching as a detection problem.<n>The goal is to identify meaningful correspondences with high precision and recall ensuring full coverage of linguistic tokens.<n>We propose an unbalanced optimal transport-based alignment model that explicitly handles distributional mismatch and structural asymmetries.
  arXiv  Detail & Related papers  (2025-09-06T05:58:52Z)
• HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation [19.997594859651233]
  HENT-SRT is a novel framework that factorizes ASR and translation tasks to better handle reordering.<n>We improve computational efficiency by incorporating best practices from ASR transducers.<n>Our approach is evaluated on three conversational datasets Arabic, Spanish, and Mandarin.
  arXiv  Detail & Related papers  (2025-06-02T18:37:50Z)
• Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer [16.716653844774374]
  We evaluate the repeatability of embeddings using the intra-class correlation coefficient (ICC) We propose a novel regularizer, the ICC regularizer, as a complementary component for contrastive losses to guide deep neural networks to produce embeddings with higher repeatability. We implement the ICC regularizer and apply it to three speech tasks: speaker verification, voice style conversion, and a clinical application for detecting dysphonic voice.
  arXiv  Detail & Related papers  (2023-10-25T23:21:46Z)
• Accented Speech Recognition With Accent-specific Codebooks [53.288874858671576]
  Speech accents pose a significant challenge to state-of-the-art automatic speech recognition (ASR) systems. Degradation in performance across underrepresented accents is a severe deterrent to the inclusive adoption of ASR. We propose a novel accent adaptation approach for end-to-end ASR systems using cross-attention with a trainable set of codebooks.
  arXiv  Detail & Related papers  (2023-10-24T16:10:58Z)
• CTC Alignments Improve Autoregressive Translation [145.90587287444976]
  We argue that CTC does in fact make sense for translation if applied in a joint CTC/attention framework. Our proposed joint CTC/attention models outperform pure-attention baselines across six benchmark translation tasks.
  arXiv  Detail & Related papers  (2022-10-11T07:13:50Z)
• Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation [62.943925893616196]
  We study the possibilities of building a non-autoregressive speech-to-text translation model using connectionist temporal classification (CTC) CTC's success on translation is counter-intuitive due to its monotonicity assumption, so we analyze its reordering capability. Our analysis shows that transformer encoders have the ability to change the word order.
  arXiv  Detail & Related papers  (2021-05-11T07:48:45Z)

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.