论文解读
FlexiVoice: Enabling Flexible Style Control in Zero-Shot TTS with Natural Language Instructions
语音合成 | 8.0/10
强化学习
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
Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
音频问答 | 8.5/10
论文解读
MARS-Sep: Multimodal-Aligned Reinforced Sound Separation
语音分离 | 7.5/10
论文解读
Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models
音频问答 | 7.5/10
论文解读
Music Flamingo: Scaling Music Understanding in Audio Language Models
音乐理解 | 7.5/10
论文解读
Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
基准测试 数据集 | 8.0/10
论文解读
ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction
语音对话系统 | 8.0/10
论文解读
PrismAudio: Decomposed Chain-of-Thought and Multi-dimensional Rewards for Video-to-Audio Generation
音频生成 | 9.0/10
论文解读
SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
语音合成 | 8.5/10
论文解读
VowelPrompt: Hearing Speech Emotions from Text via Vowel-level Prosodic Augmentation
语音情感识别 | 8.5/10
论文解读
AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
音视频 | 8.0/10
论文解读
Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
音频问答 | 8.5/10
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
Generative Adversarial Post-Training Mitigates Reward Hacking in Live Human-AI Music Interaction
音乐生成 | 8.0/10
论文解读
Human Behavior Atlas: Benchmarking Unified Psychological And Social Behavior Understanding
多模态模型 | 7.5/10
论文解读
Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards
音频问答 | 8.5/10
论文解读
MARS-Sep: Multimodal-Aligned Reinforced Sound Separation
语音分离 | 7.5/10
论文解读
Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models
音频问答 | 7.5/10