论文解读
DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations
语音对话系统 | 9.5/10
Posts
论文解读
Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
音频问答 | 8.5/10
论文解读
EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models
基准测试 | 7.0/10
论文解读
Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention
语音分离 | 7.5/10
论文解读
EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning
语音情感识别 | 8.0/10
论文解读
End-to-end Listen, Look, Speak and Act
语音对话系统 | 8.5/10
论文解读
Entropy-Monitored Kernelized Token Distillation for Audio-Visual Compression
音视频事件检测 | 8.5/10
论文解读
Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation
音频生成 | 7.5/10
论文解读
FlexiCodec: A Dynamic Neural Audio Codec for Low Frame Rates
语音合成 | 9.0/10
论文解读
FlexiVoice: Enabling Flexible Style Control in Zero-Shot TTS with Natural Language Instructions
语音合成 | 8.0/10
论文解读
Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generation
音频生成 | 8.0/10
论文解读
FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows
跨模态生成 | 9.5/10
论文解读
From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings
音频分类 | 6.5/10
论文解读
From Natural Alignment to Conditional Controllability in Multimodal Dialogue
语音合成 | 8.0/10
论文解读
From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training
语音对话系统 | 8.5/10
论文解读
GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models
音乐理解 | 7.0/10
论文解读
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
音乐生成 | 7.0/10
论文解读
Gogo: Group-wise granularity-ordered codec for stable and efficient speech generation
语音合成 | 7.5/10
论文解读
Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration
多模态模型 | 7.5/10
论文解读
Hierarchical Semantic-Acoustic Modeling via Semi-Discrete Residual Representations for Expressive End-to-End Speech Synthesis
语音合成 | 8.0/10