[评审] 利用合成交错数据扩展语音-文本预训练
原题:Scaling Speech-Text Pre-training with Synthetic Interleaved Data - 评审均分：7.0 - 决定：Accept (Poster) - 链接：https://openreview.net/forum?id=3tukjsVyrE
相关 · 按语义匹配
论文 Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
论文 Large Language Models Are Human-Level Prompt Engineers
论文 Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect
论文 A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
论文 Multimodal Speaker Verification as a Threat to Speaker Anonymization
论文 SimVLM: Simple Visual Language Model Pretraining with Weak Supervision