论文解读
SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations
语音合成 | 7.9/10
Posts
论文解读
Sensitivity Analysis of Generative Spatial Audio Metrics: A Study on Responsiveness, Smoothness, and Symmetry
音频生成 | 7.2/10
论文解读
Snapping Matters: Context-Aware Onset Refinement for Automatic Music Transcription
音乐信息检索 | 7.1/10
论文解读
SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing
模型压缩 | 7.7/10
论文解读
Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models
Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models
论文解读
The Dynamics of Human and AI-Generated Language: How Semantics Fluctuates across Different Timescales
语音合成 | 8.1/10
论文解读
The Hidden Cost of Pairwise Verification in Synthetic Speech Source Tracing
语音合成 | 7.5/10
论文解读
Tight Boundary Prediction in Speaker Diarization Using Causal-Anticausal Consistency
低资源 | 9.6/10
论文解读
Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering
语音识别 | 6.4/10
论文解读
UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction
语音合成 | 8.1/10
论文解读
Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation
语音识别 | 7.5/10
每日研究速递
语音/音乐/音频论文速递 2026-06-11
共分析 36 篇语音/AI 论文
论文解读
A Lightweight Dual-Factor Acoustic Authentication System via Cascaded GMM-DTW Architecture for Edge Computing
说话人验证 | 6/10
论文解读
ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling
语音质量评估 | 8/10
论文解读
Anchoring the Unknown: Open-Set Model Attribution via Proxy-Anchor Learning
多语言 | 8/10
论文解读
AudioProcessBench: Benchmark for Identifying Process Errors in Audio-Grounded Reasoning
AudioProcessBench: Benchmark for Identifying Process Errors in Audio-Grounded Reasoning
论文解读
AuRA: Internalizing Audio Understanding into LLMs as LoRA
语音问答 | 7.5/10
论文解读
Automated Pronunciation Evaluation for Korean Toddler Speech using Speech Diarization and Self-Supervised Learning
说话人日志 | 6/10
论文解读
ContextCodec: Content-Focused Context Guidance for Ultra-Low Bitrate Speech Coding
语音编码 | 7.9/10
论文解读
Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm
语音识别 | 7.5/10