Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictions

Documenti analoghi

• Speculative Speech Recognition by Audio-Prefixed Low-Rank Adaptation of Language Models
  di: Yusuf, Bolaji, et al.
  Pubblicazione: (2024)
• ASTRA: Aligning Speech and Text Representations for Asr without Sampling
  di: Gaur, Neeraj, et al.
  Pubblicazione: (2024)
• LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriors
  di: Ma, Rao, et al.
  Pubblicazione: (2025)
• STAB: Speech Tokenizer Assessment Benchmark
  di: Vashishth, Shikhar, et al.
  Pubblicazione: (2024)
• Zero-shot Cross-lingual Voice Transfer for TTS
  di: Biadsy, Fadi, et al.
  Pubblicazione: (2024)