论文解读
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating
扩散模型 | 8.9/10
Posts
论文解读
VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation
语音合成 | 7.6/10
论文解读
voxmap-studio: An open-source speaker diarization annotation tool with built-in cost instrumentation
说话人日志 | 6.5/10
论文解读
wav2tok 2.0: Scalable Audio Tokenization Maintaining Explicit Pairwise Token Alignment for Efficient Audio Retrieval
语音检索 | 6.4/10
论文解读
What We are Missing in Multimodal LLM Evaluation?
What We are Missing in Multimodal LLM Evaluation?
论文解读
When Does Quality-Aware Multimodal Fusion Matter? A Leakage-Safe Diagnostic for Decision-Level Dependence
语音情感识别 | 6.6/10
论文解读
WQ-Fusion: Dynamic Gated Attention for Cross-Domain Audio Representation
音频分类 | 6.7/10
每日研究速递
语音/音乐/音频论文速递 2026-06-26
共分析 22 篇语音/AI 论文
论文解读
Adaptive Oscillatory Inductive Bias for Modeling Sharp Prosodic Dynamics in Diffusion-Based TTS
语音合成 | 7/10
论文解读
Attractive and Repulsive Pattern Control in Sequence Generation
音乐生成 | 8.1/10
论文解读
BCoughBench: Benchmarking Respiratory Acoustic Foundation Models Under Body-Coupled Wearable Sensor Conditions
基准测试 | 6.7/10
论文解读
CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations
语音合成 | 5.5/10
论文解读
Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?
语音识别 | 7.1/10
论文解读
EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis
语音情感识别 | 6.9/10
论文解读
End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users
端到端 | 7/10
论文解读
Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction
语音识别 | 6.1/10
论文解读
Evaluating Japanese Dialect Robustness Across Speech and Text-based Large Language Models
语音识别 | 5.8/10
论文解读
FoleySet: A Multi-Level Human-Annotated Foley Sound Dataset
音频分类 | 7/10
论文解读
Frequency-Aware Self-Supervised Music Representation Learning
音乐信息检索 | 6.8/10
论文解读
From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models
语音识别 | 7.2/10