论文解读
MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering
音乐生成 | 7.1/10
论文速递
论文解读
MMAG: A Multi-Control Mixed Audio Generation Benchmark
音频生成 | 6.8/10
论文解读
Multi Codec Discrete Diffusion Model for Text Guided Speech Inpainting and Editing
语音编辑 | 7.3/10
论文解读
Objects as Audio-Visual Modal Sound Fields
音频生成 | 7.6/10
论文解读
SemBridge: Semantic Token Anchoring for Continuous-Latent Autoregressive Speech Generation
语音合成 | 7.0/10
论文解读
Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models
语音情感识别 | 6.8/10
论文解读
Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation
音视频交互 | 5.7/10
论文解读
StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding
多模态模型 | 7.6/10
每日研究速递
语音/音乐/音频论文速递 2026-08-10
共分析 16 篇语音/AI 论文
论文解读
A Study of ASR Adaptation and Representation Dimensionality Reduction in Persian Speech Emotion Recognition Using Whisper
语音情感识别 | 5.7/10
论文解读
AffectDF: The Most Comprehensive Benchmark for Speech Deepfake Detection against Emotionally Expressive Attacks
语音伪造检测 | 8.4/10
论文解读
Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset
音乐转录 | 7.7/10
论文解读
Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning
说话人验证 | 6.0/10
论文解读
Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors
语音质量评估 | 6.7/10
论文解读
C^3PO: Evaluating Cross-Modal Composition and Counterfactual Performance in Omnimodal Models
音视频问答 | 5.5/10
论文解读
Decolonizing Linguistic Policies in Automated Speech Recognition: A Framework for Cross-Culturally Competent Speech AI
语音识别 | 7.8/10
论文解读
Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model
音乐生成 | 6.5/10
论文解读
Diff2Mix: Controllable Music Mixing via Diffusion Models and Differentiable Audio Effects
音频生成 | 7.5/10
论文解读
ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment
语音属性识别 | 5.5/10
论文解读
EG-VAE: A Unified Framework for Electric Guitar Tone Transfer and Removal
音频生成 | 7.3/10