每日研究速递
语音/音乐/音频论文速递 2026-07-13
共分析 14 篇语音/AI 论文
强化学习
论文解读
Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech
语音识别 | 7.0/10
论文解读
MuScriptor: An Open Model for Multi-Instrument Music Transcription
音乐转录 | 8.3/10
论文解读
MuScriptor: An Open Model for Multi-Instrument Music Transcription
音乐转录 | 9.2/10
论文解读
When Synthetic Speech Is All You Have: Better Call GRPO
语音识别 | 7.7/10
论文解读
When Synthetic Speech Is All You Have: Better Call GRPO
语音识别 | 7.8/10
论文解读
Reinforcement Learning for Data-Efficient Code-Switched ASR
语音识别 | 5.3/10
论文解读
Unified Audio Intelligence Without Regressing on Text Intelligence
音频交互 | 6.8/10
论文解读
ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools — From Consensus Learning to Ambiguity-Driven Emotion Reasoning
语音情感识别 | 6.5/10
论文解读
AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning
音频理解 | 6.2/10
论文解读
E-VAds: An E-commerce Short Videos Understanding Benchmark for MLLMs
音视频问答 | 6.9/10
论文解读
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability
语音合成 | 6.6/10
论文解读
Multimodal Meta-Verifier with Explicit Structured Recalibration
多模态模型 | 5.2/10
论文解读
OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention
音视频问答 | 7.5/10
论文解读
Simultaneous Speech-to-Speech Translation Without Aligned Data
语音翻译 | 8/10
论文解读
TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
音视频理解 | 9.4/10
论文解读
Decomposer: Learning to Decompile Symbolic Music to Programs
音乐理解 | 8.4/10
论文解读
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
音视频理解 | 7.2/10
论文解读
Proteus: Automated Adversarial Robustness Testing for Audio Deepfake Detectors
数据增强 | 5.3/10
论文解读
MER-R1: Multimodal Emotion Reasoning via Slow-Fast Thinking Synergy
多模态模型 | 7.4/10