论文解读

PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement

语音增强 | 8.1/10

 · 更新于 2026-11-05 · 约 16 分钟 · 7802 字 阅读 →
论文解读

StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement

语音增强 | 7.0/10

 · 更新于 2026-11-05 · 约 15 分钟 · 7515 字 阅读 →
论文解读

Anomalous Sound Detection Meets Noise-Aware Self-Supervised Learning

音频事件检测 | 7.2/10

 · 更新于 2026-11-05 · 约 14 分钟 · 6649 字 阅读 →
论文解读

Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR

语音识别 | 6.9/10

 · 更新于 2026-11-05 · 约 13 分钟 · 6440 字 阅读 →
论文解读

LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation

音视频生成 | 6.8/10

 · 更新于 2026-11-05 · 约 17 分钟 · 8468 字 阅读 →
论文解读

AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition

语音情感识别 | 5.6/10

 · 更新于 2026-11-05 · 约 12 分钟 · 5579 字 阅读 →
论文解读

Parallel Decoding Distillation for Fast Image and Video Generation

音视频生成 | 6.2/10

 · 更新于 2026-11-05 · 约 19 分钟 · 9236 字 阅读 →
论文解读

OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

音视频生成 | 7.1/10

 · 更新于 2026-11-05 · 约 16 分钟 · 7731 字 阅读 →
论文解读

OPOD: On-Policy Omni Distillation

多模态模型 | 7.1/10

 · 更新于 2026-11-05 · 约 14 分钟 · 6936 字 阅读 →
论文解读

X^3-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment

音频理解 | 7.1/10

 · 更新于 2026-11-05 · 约 17 分钟 · 8383 字 阅读 →
论文解读

Staged Depth-Pruning Distillation of a Flow-Matching Text-to-Speech Teacher: A Compact Hindi Speech Synthesizer

语音合成 | 7.9/10

 · 更新于 2026-11-05 · 约 17 分钟 · 8461 字 阅读 →
论文解读

Do Speech Tokens Leak Voiceprints? Speaker Inversion Attacks Against End-to-End Speech Language Models

说话人验证 | 7.7/10

 · 更新于 2026-11-05 · 约 17 分钟 · 8389 字 阅读 →
论文解读

Efficient Audio-Visual Event Recognition via Knowledge Distillation and Dynamic INT8 Quantization of a Hybrid Cross-Attention Network

音视频理解 | 5.8/10

 · 更新于 2026-11-05 · 约 12 分钟 · 5753 字 阅读 →
论文解读

NABEATs: Noise-Aware Audio Representation Learning

音频理解 | 6.7/10

 · 更新于 2026-11-05 · 约 18 分钟 · 8604 字 阅读 →
论文解读

Pseudo-label distillation for discriminative anomalous sound detection

音频事件检测 | 9.0/10

 · 更新于 2026-11-05 · 约 15 分钟 · 7353 字 阅读 →
论文解读

Data-driven Video Codec with Implicit Neural Representations

音频编码 | 5.3/10

 · 更新于 2026-11-05 · 约 14 分钟 · 6797 字 阅读 →
论文解读

From Prediction to Collaboration: Interactive Symbolic Music Analysis

音乐理解 | 7.5/10

 · 更新于 2026-11-05 · 约 13 分钟 · 6028 字 阅读 →
论文解读

Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?

语音情感识别 | 7.4/10

 · 更新于 2026-11-05 · 约 14 分钟 · 6817 字 阅读 →
论文解读

It Takes Few to TANGO: A Quantized Distributed Model for Binaural Speech Enhancement

语音增强 | 6.5/10

 · 更新于 2026-11-05 · 约 19 分钟 · 9170 字 阅读 →
论文解读

Audio Sentiment Analysis via Distillation and Cross-Modal Integration of Generated Multilingual Transcripts

语音情感识别 | 6.9/10

 · 更新于 2026-11-05 · 约 17 分钟 · 8349 字 阅读 →