论文解读
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
语音合成 | 8.9/10
数据增强
论文解读
Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs
语音识别 | 7.2/10
论文解读
EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs
强化学习 | 9.1/10
论文解读
Raon-Speech Technical Report
语音识别 | 6.5/10
每日研究速递
语音/音乐/音频论文速递 2026-05-30
共分析 6 篇语音/AI 论文
论文解读
Archon: A Unified Multimodal Model for Holistic Digital Human Generation
语音合成 | 7.5/10
论文解读
Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
多模态模型 | 8.9/10
论文解读
Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking
语音合成 | 8.6/10
论文解读
Mitigating Stethoscope-Induced Shortcuts in Respiratory Sound Classification under Federated Domain Generalization with Causality-Inspired Interventions
音频分类 | 8.5/10
论文解读
Dasheng AudioGen: A Unified Model for Generating Coherent Audio Scenes from Text
音频生成 | 8.6/10
论文解读
Diffusion Large Language Models for Visual Speech Recognition
语音识别 | 7.0/10
论文解读
Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts
语音合成 | 8/10
论文解读
When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR
语音识别 | 10/10
论文解读
Why We Need Speech to Evaluate Speech Translation
语音翻译 | 8.3/10
论文解读
CosyEdit2: Speech-Editing-Oriented Reinforcement Learning Unlocks Better Zero-Shot TTS
语音编辑 | 7.2/10
论文解读
MERIT: Learning Disentangled Music Representations for Audio Similarity
音频检索 | 9/10
论文解读
PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis
语音合成 | 9.2/10
论文解读
Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
语音识别 | 7.5/10
论文解读
CosyEdit2: Speech-Editing-Oriented Reinforcement Learning Unlocks Better Zero-Shot TTS
语音合成 | 8/10
论文解读
Music Transcription with (Almost) No Supervision
音乐转录 | 10/10