mlsanityData to 14 Oct 2026

Low-Burden Data Augmentation for Dysarthric ASR via Zero-Shot Voice Cloning

arXiv 2606.19823 ↗First posted 18 Jun 2026eess.AS cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Automatic speech recognition remains unreliable for dysarthric speech due to data scarcity and high inter-speaker variability. While synthetic data can address these gaps, traditional methods often require extensive speaker-specific data, reintroducing the collection bottleneck. We investigate zero-shot voice cloning as a low-burden augmentation strategy, using Higgs Audio V2 to clone speakers in the TORGO dataset. We fine-tune (FT) Whisper-medium on cloned, real, and hybrid data and evaluate on held-out real speech. Compared to the zero-shot (31.62%), Clone FT achieved a competitive 26.00% WER, nearly matching the 24.44% and 25.12% seen with Real and Hybrid FT, respectively. Notably, Clone and Hybrid FT outperform Real FT for moderate-severe speakers. Clone FT achieves the best results (11.45% relative) in cross-corpus evaluation on the SAP-1102. These results suggest that zero-shot cloning provides scalable training data that circumvents the costly data collection bottleneck.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 30 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

14 of 30 references.

References · 14

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  4. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  5. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 278
  6. 2024VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizerscited by 122
  7. 2021TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global contextcited by 62
  8. 2018Simulating dysarthric speech for training data augmentation in clinical speech applicationscited by 14
  9. 2024Training Data Augmentation for Dysarthric Automatic Speech Recognition by Text-to-Dysarthric-Speech Synthesiscited by 14
  10. 2021Towards Identity Preserving Normal to Dysarthric Voice Conversioncited by 10
  11. 2023Accurate synthesis of Dysarthric Speech for ASR data augmentationcited by 7
  12. 2025Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognitioncited by 6
2 more
  1. 2023PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognitioncited by 1
  2. 2025Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognitioncited by 1

Built on by

Not cited yet.