Instruction Data Generation and Unsupervised Adaptation for Speech Language Models

Documenti analoghi

• Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition
  di: Noroozi, Vahid, et al.
  Pubblicazione: (2023)
• DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data
  di: Lu, Ke-Han, et al.
  Pubblicazione: (2024)
• Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR
  di: Wang, Weiqing, et al.
  Pubblicazione: (2024)
• SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model
  di: Hu, Ke, et al.
  Pubblicazione: (2025)
• VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning
  di: Peng, Yifan, et al.
  Pubblicazione: (2024)