ICASSP 2026 - 音频检索 论文列表
ICASSP 2026 - 音频检索 共 11 篇论文 ← 返回 ICASSP 2026 总览 排名 论文 评分 分档 🥇 GLAP: General Contrastive Audio-Text Pretraining Across Doma 8.5分 前25% 🥈 CASTELLA: Long Audio Dataset with Captions and Temporal Boun 8.5分 前25% 🥉 WavLink: Compact Audio–Text Embeddings with a Global Whisper 8.0分 前25% 4. SLAP: Scalable Language-Audio Pretraining with Variable-Dura 8.0分 前25% 5. AUDIOCARDS: Structured Metadata Improves Audio Language Mode 7.5分 前50% 6. Automatic Music Sample Identification with Multi-Track Contr 7.5分 前25% 7. Contrastive Timbre Representations for Musical Instrument An 7.5分 前25% 8. BEST-STD 2.0: Balanced and Efficient Speech Tokenizer for Sp 7.5分 前25% 9. EchoRAG: A Two-Stage Framework for Audio-Text Retrieval and 7.5分 前25% 10. Scalable Evaluation for Audio Identification Via Synthetic L 7.0分 前25% 11. Do Speech LLMs Learn Crossmodal Embedding Spaces? 6.5分 前50% 📋 论文详情 🥇 GLAP: General Contrastive Audio-Text Pretraining Across Domains and Languages 🔥 8.5/10 | 前25% | #音频检索 | #对比学习 #预训练 | #对比学习 #预训练 ...