论文解读
UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment
语音质量评估 | 10/10
强化学习
每日研究速递
语音/音乐/音频论文速递 2026-05-25
共分析 19 篇语音/AI 论文
论文解读
A conceptual framework for learning to listen by reward: Curiosity-driven search for novel sources
声源定位 | 4.0/10
论文解读
A Survey of Audio Reasoning in Multimodal Foundation Models
音频推理 | 7.7/10
论文解读
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
语音识别 | 9.3/10
论文解读
Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
音频编码 | 6.5/10
论文解读
Thinking-while-speaking: A Controlled, Interleaved Reasoning Method for Real-Time Speech Generation
语音对话系统 | 6.9/10
论文解读
A conceptual framework for learning to listen by reward: Curiosity-driven search for novel sources
声源定位 | 5/10
论文解读
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
语音识别 | 6.8/10
论文解读
Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
音频编码 | 7/10
论文解读
EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
多智能体协同 | 8.0/10
论文解读
OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
音视频生成 | 6.9/10
论文解读
Evaluating the Expressive Appropriateness of Speech in Rich Contexts
语音质量评估 | 7.2/10
论文解读
Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization
基准测试 | 6.5/10
论文解读
Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought
音视频问答 | 6.0/10
论文解读
Stage Light is Sequence^2: Multi-Light Control via Imitation Learning
舞台技术 | 7.0/10
论文解读
To Fuse or to Drop? Dual-Path Learning for Resolving Modality Conflicts in Multimodal Emotion Recognition
语音情感识别 | 8.0/10
论文解读
Stage Light is Sequence$^2$: Multi-Light Control via Imitation Learning
音乐信息检索 | 7.5/10
论文解读
NH-CROP: Robust Pricing for Governed Language Data Assets under Cost Uncertainty
强化学习 | 7.5/10
论文解读
AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
视频描述生成 | 8.5/10