论文解读

Perforated Neural Networks for Keyword Spotting

关键词检测 | 5/10

 · 更新于 2026-09-25 · 约 15 分钟 · 7432 字 阅读 →
论文解读

OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models

音视频 | 7.0/10

 · 更新于 2026-09-25 · 约 17 分钟 · 8379 字 阅读 →
论文解读

Entropy-Monitored Kernelized Token Distillation for Audio-Visual Compression

音视频事件检测 | 8.5/10

 · 更新于 2026-09-25 · 约 11 分钟 · 5068 字 阅读 →
论文解读

Cross-Architecture Knowledge Distillation of WavLM for Lightweight Speaker Verification

说话人验证 | 8.0/10

 · 更新于 2026-09-25 · 约 13 分钟 · 6123 字 阅读 →
论文解读

Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation Guided Structured Pruning

说话人验证 | 7.5/10

 · 更新于 2026-09-25 · 约 10 分钟 · 4903 字 阅读 →
论文解读

Lightweight and Generalizable Acoustic Scene Representations Via Contrastive Fine-Tuning and Distillation

音频场景理解 | 8.0/10

 · 更新于 2026-09-25 · 约 11 分钟 · 5226 字 阅读 →
论文解读

MAGE: A Coarse-to-Fine Speech Enhancer with Masked Generative Model

语音增强 | 8.0/10

 · 更新于 2026-09-25 · 约 12 分钟 · 5811 字 阅读 →
论文解读

S-SONDO: Self-Supervised Knowledge Distillation for General Audio Foundation Models

音频分类 | 7.0/10

 · 更新于 2026-09-25 · 约 9 分钟 · 4416 字 阅读 →
论文解读

Transferable Audio Lottery Tickets: Gradient Accumulation for Extreme Sparsity

音频分类 | 7.0/10

 · 更新于 2026-09-25 · 约 8 分钟 · 3873 字 阅读 →
论文解读

Triage Knowledge Distillation for Speaker Verification

说话人验证 | 7.5/10

 · 更新于 2026-09-25 · 约 10 分钟 · 4613 字 阅读 →
论文解读

What the student learns in knowledge distillation: A subspace view and evidence on Convolutional Recurrent Network

语音增强 | 6.5/10

 · 更新于 2026-09-25 · 约 9 分钟 · 4287 字 阅读 →