Personalized Fine-Tuning with Controllable Synthetic Speech from LLM-Generated Transcripts for Dysarthric Speech Recognition

Documenti analoghi

• Large Language Models for Dysfluency Detection in Stuttered Speech
  di: Wagner, Dominik, et al.
  Pubblicazione: (2024)
• Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models
  di: Wagner, Dominik, et al.
  Pubblicazione: (2024)
• Vocoder-Free Non-Parallel Conversion of Whispered Speech With Masked Cycle-Consistent Generative Adversarial Networks
  di: Wagner, Dominik, et al.
  Pubblicazione: (2023)
• Time vs. Layer: Locating Predictive Cues for Dysarthric Speech Descriptors in wav2vec 2.0
  di: Engert, Natalie, et al.
  Pubblicazione: (2026)
• Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0
  di: Bayerl, Sebastian P., et al.
  Pubblicazione: (2022)