论文解读
不抄答案抄思路：把蒸馏钉在量化器之前
语音识别 | 6.9/10
模型压缩
论文解读
压住房间的尾音：375bps 里留住混响的衰减骨架
音频编码 | 6.6/10
论文解读
开耳助听器里漏进来的噪声，为何要让扬声器自己去抵消？
语音增强 | 7.5/10
论文解读
1500 个音频 token 真的都需要吗？用等间隔抽样戳破 Whisper 的时域冗余
语音识别 | 7.2/10
论文解读
把教师的回声残差教给小模型：AEC 蒸馏到底补回了什么
回声消除 | 8.5/10
论文解读
A Regularized Block Diagonal RLS Algorithm for Acoustic Echo Cancellation
回声消除 | 7.2/10
论文解读
PolyChirp: Multi-Species Birdsong Classification Using TinyML on Low-Power Acoustic Sensors
音频分类 | 10.0/10
论文解读
sanoTTS: The Smallest Real-Time Neural TTS on a General-Purpose Microcontroller
语音合成 | 10.0/10
论文解读
SlimDiffuSE: Towards Efficient Diffusion-Based Speech Enhancement using Slimmable Networks
语音增强 | 7.6/10
论文解读
μNet: Ultra-Low-Memory and Low-Complexity Speech Enhancement for Embedded Digital Signal Processors
语音增强 | 8.3/10
论文解读
DAVSS: Distilled Audio-Visual State Space Models
音视频理解 | 6.4/10
论文解读
AudioTQ: A Data-Oblivious 6-Bit CPU Audio Codec via Randomized Hadamard Rotation and Lloyd-Max Quantization
音频编码 | 3.5/10
论文解读
RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation
语音增强 | 6.6/10
论文解读
Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMs
模型剪枝 | 8.4/10
论文解读
omni-macos: On-Device Omni-Modal Search on Apple Silicon
音频检索 | 7.2/10
论文解读
VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference
音频理解 | 7.7/10
论文解读
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models
音视频理解 | 7.7/10
论文解读
AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition
语音情感识别 | 5.6/10
论文解读
faster-enhancer.c: A Dependency-Free int8 Runtime for Streaming Speech Enhancement on Commodity CPUs
语音增强 | 8.7/10
论文解读
OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs
音视频问答 | 7.0/10