Phoneme-based speech recognition driven by large language models and sampling marginalization

Documenti analoghi

• LLM-based phoneme-to-grapheme for phoneme-based speech recognition
  di: Ma, Te, et al.
  Pubblicazione: (2025)
• Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition
  di: Dong, Lukuang, et al.
  Pubblicazione: (2026)
• CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment
  di: Liu, Hanwen, et al.
  Pubblicazione: (2026)
• Robust fine-tuning of speech recognition models via model merging: application to disordered speech
  di: Ducorroy, Alexandre, et al.
  Pubblicazione: (2025)
• Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervision
  di: Yusuyin, Saierdaer, et al.
  Pubblicazione: (2024)