论文解读

TRACE-EVC: Text-Guided Relative Affective Control for Zero-Shot Emotional Voice Conversion

语音转换 | 8/10

 · 更新于 2026-09-06 · 约 12 分钟 · 5784 字 阅读 →
论文解读

Training-Free Model Selection and Domain-Aware Score Calibration for First-Shot Anomalous Sound Detection

音频事件检测 | 7.3/10

 · 更新于 2026-09-06 · 约 16 分钟 · 7682 字 阅读 →
论文解读

Trajectory Variance: AnUnsupervised Measure of Developmental Vocal Plasticity in Birdsong

音频理解 | 6.2/10

 · 更新于 2026-09-06 · 约 11 分钟 · 5458 字 阅读 →
论文解读

Unified Audio Intelligence Without Regressing on Text Intelligence

音频交互 | 6.8/10

 · 更新于 2026-09-06 · 约 7 分钟 · 3294 字 阅读 →
论文解读

UniSkip-Mamba: A Frequency-Aware State Space Model for Audio-Visual Temporal Forgery Localization

音视频理解 | 4.8/10

 · 更新于 2026-09-06 · 约 13 分钟 · 6505 字 阅读 →
论文解读

Wan-Streamer v0.2: Higher Resolution, Same Latency

音视频交互 | 5.4/10

 · 更新于 2026-09-06 · 约 11 分钟 · 5455 字 阅读 →
论文解读

Weakly Guided and Autoregressive Beamformer Parameterization for Generalizable Moving Speaker Extraction in Higher-Order Ambisonics

语音分离 | 4.3/10

 · 更新于 2026-09-06 · 约 10 分钟 · 4977 字 阅读 →
每日研究速递

语音/音乐/音频论文速递 2026-07-07

共分析 58 篇语音/AI 论文

 · 更新于 2026-09-06 · 约 176 分钟 · 87928 字 阅读 →
论文解读

VisionAId: An Offline-First Multimodal Android Assistant for People with Visual Impairment, Featuring Personalized Object Retrieval

音视频交互 | 6.6/10

 · 更新于 2026-09-06 · 约 14 分钟 · 6871 字 阅读 →
每日研究速递

语音/音乐/音频论文速递 2026-07-06

共分析 1 篇语音/AI 论文

 · 更新于 2026-09-06 · 约 3 分钟 · 1340 字 阅读 →
论文解读

\(\tau\)-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains

语音交互 | 9.1/10

 · 更新于 2026-09-06 · 约 18 分钟 · 8721 字 阅读 →
论文解读

A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation

音频分离 | 9.2/10

 · 更新于 2026-09-06 · 约 13 分钟 · 6048 字 阅读 →
论文解读

Abstraction Induces the Brain Alignment of Language and Speech Models

语音编码 | 7.5/10

 · 更新于 2026-09-06 · 约 12 分钟 · 5709 字 阅读 →
论文解读

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models

音频理解 | 8/10

 · 更新于 2026-09-06 · 约 17 分钟 · 8490 字 阅读 →
论文解读

ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools — From Consensus Learning to Ambiguity-Driven Emotion Reasoning

语音情感识别 | 6.5/10

 · 更新于 2026-09-06 · 约 20 分钟 · 9724 字 阅读 →
论文解读

AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching

语音合成 | 7.6/10

 · 更新于 2026-09-06 · 约 16 分钟 · 7803 字 阅读 →
论文解读

AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech

语音合成 | 7.9/10

 · 更新于 2026-09-06 · 约 17 分钟 · 8042 字 阅读 →
论文解读

Alethia: a Foundational Encoder for Voice Deepfakes

语音伪造检测 | 7.6/10

 · 更新于 2026-09-06 · 约 14 分钟 · 6803 字 阅读 →
论文解读

An Exterior Method for Nonnegative Matrix Factorization

音频分类 | 6.8/10

 · 更新于 2026-09-06 · 约 14 分钟 · 6581 字 阅读 →
论文解读

Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses

音视频理解 | 7.8/10

 · 更新于 2026-09-06 · 约 11 分钟 · 5380 字 阅读 →