MTLM: Incorporating Bidirectional Text Information to Enhance Language Model Training in Speech Recognition Systems

Documenti analoghi

• FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis
  di: Meng, Qingliang, et al.
  Pubblicazione: (2025)
• Incorporating Class-based Language Model for Named Entity Recognition in Factorized Neural Transducer
  di: Wang, Peng, et al.
  Pubblicazione: (2023)
• Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition
  di: Cornell, Samuele, et al.
  Pubblicazione: (2024)
• DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment
  di: Lu, Ke-Han, et al.
  Pubblicazione: (2024)
• Speech Recognition Model Improves Text-to-Speech Synthesis using Fine-Grained Reward
  di: Wang, Guansu, et al.
  Pubblicazione: (2025)