论文解读
C2GA: A Class-Controllable Generative Augmentation Framework for Respiratory Sound Classification
音频分类 | 7.3/10
数据增强
论文解读
CoughSense: Five-Class Respiratory Disease Classification via Whisper Encoder Fine-Tuning and Dual-Encoder Cross-Attention Fusion with Balanced Contrastive Learning
数据增强 | 9.1/10
论文解读
Efficient ASR Training with Conversations that Never Happened
语音识别 | 8/10
论文解读
SegTune: Structured and Fine-Grained Control for Song Generation
音乐生成 | 8.5/10
论文解读
SiamCTC: Learning Speech Representations through Monotonic Temporal Alignment
语音识别 | 7/10
论文解读
SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling
音乐生成 | 8.6/10
论文解读
Advancing Electrolaryngeal Speech Enhancement Through Speech-Text Representation Learning
语音增强 | 7.1/10
论文解读
AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
多模态模型 | 7/10
论文解读
Echo: A Joint-Embedding Predictive Architecture for Speaker Diarization and Speech Recognition in a Shared Latent Space
语音识别 | 7/10
论文解读
UniVocal: Unified Speech-Singing Code-Switching Synthesis
语音合成 | 8.9/10
论文解读
ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment
语音合成 | 9.3/10
论文解读
Improving acoustic drone detection generalization through pretraining and data augmentation
音频事件检测 | 7.7/10
论文解读
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
语音合成 | 8.9/10
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