InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training

Documenti analoghi

• MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark
  di: Wang, Dingdong, et al.
  Pubblicazione: (2025)
• A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models
  di: Wang, Dingdong, et al.
  Pubblicazione: (2024)
• Scaling Speech-Text Pre-training with Synthetic Interleaved Data
  di: Zeng, Aohan, et al.
  Pubblicazione: (2024)
• SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models
  di: Yang, Dongchao, et al.
  Pubblicazione: (2024)
• CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction
  di: Chen, Xueyuan, et al.
  Pubblicazione: (2024)