Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition

• URL: http://arxiv.org/abs/2605.13087v1
• Date: Wed, 13 May 2026 06:55:55 GMT
• Title: Vividh-ASR: A Complexity-Tiered Benchmark and Optimization Dynamics for Robust Indic Speech Recognition
• Abstract summary: Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance.<n>We introduce Vividh-ASR, a benchmark for Hindi and Malayalam across four tiers: studio, broadcast, spontaneous, complexity, and synthetic noise.<n>We find that early large parameter updates improve global WER by 12 absolute points, while a hard-to-easy curriculum adds gains for spontaneous speech.
• Score: 0.34797121357690153
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Fine-tuning multilingual ASR models like Whisper for low-resource languages often improves read speech but degrades spontaneous audio performance, a phenomenon we term studio-bias. To diagnose this mismatch, we introduce Vividh-ASR, a complexity-stratified benchmark for Hindi and Malayalam across four tiers: studio, broadcast, spontaneous, and synthetic noise. Through a controlled study of learning-rate timing and curriculum ordering, we find that early large parameter updates improve global WER by 12 absolute points, while a hard-to-easy curriculum adds gains for spontaneous speech. These findings motivate reverse multi-stage fine-tuning (R-MFT), a training recipe that enables a parameter-efficient 244M Whisper model to match or exceed conventionally fine-tuned 769M counterparts. Representational analysis via CKA and SVD reveals effective schedules concentrate adaptation in the decoder, preserving the pre-trained encoder's acoustic geometry. We release the benchmark and models.

Related papers

• Boosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards [8.109014000578766]
  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.
  arXiv  Detail & Related papers  (2026-03-05T14:43:15Z)
• Harmonizing the Arabic Audio Space with Data Scheduling [15.84874997729878]
  This paper presents the first systematic study of multi-task instruction tuning for an Arabic-centric audio LLM.<n>We fine-tune Qwen2.5- Omni (7B) and propose Task-Progressive Curriculum (TPC) along with Aligner-Based Diverse Sampling (ADS)<n>Our results reveal a critical efficiency, robustness trade-off: while ADS accelerates initial convergence, its inherent gradient volatility can destabilize generative decoding under prolonged training.
  arXiv  Detail & Related papers  (2026-01-18T17:08:31Z)
• Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet [72.53502346791814]
  We compare flat-start training across datasets, SSL representations (WavLM, XEUS), and decoder architectures.<n> SSL representations are biased toward adult speech, with flat-start training on child speech mitigating these biases.<n>Age-related ASR and speaker verification analysis highlights the limitations of proprietary models.
  arXiv  Detail & Related papers  (2025-08-22T17:59:35Z)
• AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition [5.916484958997203]
  AS-ASR is a lightweight aphasia-specific speech recognition framework based on Whisper-tiny.<n>Our approach systematically combines standard and aphasic speech at varying ratios, enabling robust generalization.
  arXiv  Detail & Related papers  (2025-06-06T22:38:53Z)
• DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis [12.310318928818546]
  We introduce DMOSpeech, a distilled diffusion-based TTS model that achieves both faster inference and superior performance compared to its teacher model.<n>Our comprehensive experiments, validated through extensive human evaluation, show significant improvements in naturalness, intelligibility, and speaker similarity while reducing inference time by orders of magnitude.<n>This work establishes a new framework for aligning speech synthesis with human auditory preferences through direct metric optimization.
  arXiv  Detail & Related papers  (2024-10-14T21:17:58Z)
• Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs [3.8300818830608345]
  Multi-modal contrastive learning strategies for audio and text have rapidly gained interest.<n>The ability of these models to understand natural language and temporal relations is still a largely unexplored and open field for research.<n>We propose to equip the multi-modal ALMs with temporal understanding without loosing their inherent prior capabilities of audio-language tasks with a temporal instillation method TeminAL.
  arXiv  Detail & Related papers  (2024-08-17T18:53:17Z)
• Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer [59.57249127943914]
  We present a multilingual Audio-Visual Speech Recognition model incorporating several enhancements to improve performance and audio noise robustness. We increase the amount of audio-visual training data for six distinct languages, generating automatic transcriptions of unlabelled multilingual datasets. Our proposed model achieves new state-of-the-art performance on the LRS3 dataset, reaching WER of 0.8%.
  arXiv  Detail & Related papers  (2024-03-14T01:16:32Z)
• Large Language Models are Efficient Learners of Noise-Robust Speech Recognition [65.95847272465124]
  Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR) In this work, we extend the benchmark to noisy conditions and investigate if we can teach LLMs to perform denoising for GER. Experiments on various latest LLMs demonstrate our approach achieves a new breakthrough with up to 53.9% correction improvement in terms of word error rate.
  arXiv  Detail & Related papers  (2024-01-19T01:29:27Z)
• Continual Learning for On-Device Speech Recognition using Disentangled Conformers [54.32320258055716]
  We introduce a continual learning benchmark for speaker-specific domain adaptation derived from LibriVox audiobooks. We propose a novel compute-efficient continual learning algorithm called DisentangledCL. Our experiments show that the DisConformer models significantly outperform baselines on general ASR.
  arXiv  Detail & Related papers  (2022-12-02T18:58:51Z)
• Discretization and Re-synthesis: an alternative method to solve the Cocktail Party Problem [65.25725367771075]
  This study demonstrates, for the first time, that the synthesis-based approach can also perform well on this problem. Specifically, we propose a novel speech separation/enhancement model based on the recognition of discrete symbols. By utilizing the synthesis model with the input of discrete symbols, after the prediction of discrete symbol sequence, each target speech could be re-synthesized.
  arXiv  Detail & Related papers  (2021-12-17T08:35:40Z)
• Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction [109.44933866397123]
  Noise robustness is essential for deploying automatic speech recognition systems in real-world environments. We employ a noise-robust representation learned by a refined self-supervised framework for noisy speech recognition. We achieve comparable performance to the best supervised approach reported with only 16% of labeled data.
  arXiv  Detail & Related papers  (2021-10-28T20:39:02Z)

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.