论文解读
REIMU: Efficient Heterogeneous Hierarchical Reasoning for SSL-Based Speech Deepfake Detection
语音伪造检测 | 6.4/10
参数高效微调
子标签
下方只统计已核验方向的论文记录，按已核身份去重，身份待核时按页面保留。“直接”只含明确标注该方向的论文；“含子树”同时包含下级方向。点击名称进入论文库继续筛选；数量与上方按标签名称收录的页面数不同。
每日研究速递
语音/音乐/音频论文速递 2026-08-04
共分析 39 篇语音/AI 论文
论文解读
Enhancing Law-Enforcement Audio Transcription: A LoRA-Based Adaptation of Whisper for BWC Footage
语音识别 | 4.8/10
每日研究速递
语音/音乐/音频论文速递 2026-07-31
共分析 16 篇语音/AI 论文
论文解读
DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues
语音交互 | 6.5/10
每日研究速递
语音/音乐/音频论文速递 2026-07-30
共分析 19 篇语音/AI 论文
论文解读
From Semantics to Readout: Mechanistic Understanding of Audio Tokens after Fine-Tuning for Temporal Audio Grounding
音频理解 | 5.1/10
论文解读
Text-Prompted CLAP: Learning Query-Conditioned Audio Representations via Contrastive Learning
音频理解 | 6.6/10
每日研究速递
语音/音乐/音频论文速递 2026-07-29
共分析 27 篇语音/AI 论文
论文解读
Automatic Audio Equalization with Semantic Embeddings
语音增强 | 5.8/10
论文解读
MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition
语音识别 | 6.7/10
论文解读
Music-Source-Separation-Training (MSST): A Unified Framework for Training and Evaluating Music Demixing Models
音乐源分离 | 5.7/10
每日研究速递
语音/音乐/音频论文速递 2026-07-28
共分析 31 篇语音/AI 论文
论文解读
Listen, Do Not Copy: Internalizing Audio-Grounded Scaffold Context for Robust Omni-Model Speech Understanding
语音识别 | 6.6/10
论文解读
MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond
语音识别 | 8.2/10
每日研究速递
语音/音乐/音频论文速递 2026-07-27
共分析 13 篇语音/AI 论文
论文解读
Cumsum-Composable Phase Transport for Low-Cost Streaming Keyword Spotting
语音唤醒 | 5.9/10
论文解读
Scalable Keyword Spotting via Modular Network Expansion
语音唤醒 | 7.1/10
论文解读
SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision
语音翻译 | 7.3/10
每日研究速递
语音/音乐/音频论文速递 2026-07-23
共分析 21 篇语音/AI 论文