Spelling Correction through Rewriting of Non-Autoregressive ASR Lattices

Documenti analoghi

• High-precision Voice Search Query Correction via Retrievable Speech-text Embedings
  di: Li, Christopher, et al.
  Pubblicazione: (2024)
• EffectiveASR: A Single-Step Non-Autoregressive Mandarin Speech Recognition Architecture with High Accuracy and Inference Speed
  di: Zhuang, Ziyang, et al.
  Pubblicazione: (2024)
• SOA: Reducing Domain Mismatch in SSL Pipeline by Speech Only Adaptation for Low Resource ASR
  di: Shankar, Natarajan Balaji, et al.
  Pubblicazione: (2024)
• Unifying Streaming and Non-streaming Zipformer-based ASR
  di: Sharma, Bidisha, et al.
  Pubblicazione: (2025)
• UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models
  di: Guan, Wenhao, et al.
  Pubblicazione: (2025)