语音合成论文趋势 2023–2026

主要结论

• 语音合成论文从 2023 年的 125 篇增长到 2026 年的 200 篇，三年间扩大到约 1.6 倍。
• NeurIPS 是发语音合成论文最多的会议，2023–2026 年共 204 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是目标检测：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 10 篇。
• 在「语音与音频」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的音频生成是 4.3 倍，语音合成是 1.6 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026CAPER: Clause-Aligned Process Supervision for Text-to-SQL
• ICML 2026Black-Box Detection of LLM-Generated Text Using Generalized Jensen Shannon Divergence
• ICLR 2026CSRv2: Unlocking Ultra-Sparse Embeddings
• CVPR 2026Aligning Text Images and 3D Structure Token-by-Token
• NeurIPS 2025AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
• ICML 2025How to Synthesize Text Data without Model Collapse?
• ICLR 2025AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
• CVPR 2025AMO Sampler: Enhancing Text Rendering with Overshooting
• NeurIPS 2024SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark
• ICML 2024Adaptive Text Watermark for Large Language Models
• ICLR 2024Are Models Biased on Text without Gender-related Language?
• CVPR 2024Kernel Adaptive Convolution for Scene Text Detection via Distance Map Prediction
• NeurIPS 2023[Re] Pure Noise to the Rescue of Insufficient Data
• ICML 2023Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
• ICLR 2023Bag of Tricks for Unsupervised Text-to-Speech
• CVPR 20233D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions
• NeurIPS 2026DiffScore: Text Evaluation Beyond Autoregressive Likelihood
• ICML 2026CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
• ICLR 2026DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations
• CVPR 2026Learning complete and explainable visual representations from itemized text supervision

全部语音合成论文

共 195 篇，第 1 / 4 页

1. CVPR 2026A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene
2. CVPR 2026AdaIAT Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations
3. CVPR 2026Aligning Text Images and 3D Structure Token-by-Token
4. CVPR 2026Beyond Text Prompts Precise Concept Erasure through Text-Image Collaboration
5. CVPR 2026Beyond Text Visual Description Assembly by Probabilistic Model for CLIP-based
6. CVPR 2026CoordSpeaker Exploiting Gesture Captioning for Coordinated Caption-Empowered Co-Speech Gesture Generation
7. CVPR 2026Cross from Left to Right Brain Adaptive Text Dreamer for
8. CVPR 2026Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based
9. CVPR 2026CSF Black-box Fingerprinting via Compositional Semantics for Text-to-Image Models
10. CVPR 2026CTCal Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration
11. CVPR 2026Detect Any AI-Counterfeited Text Image
12. CVPR 2026DiffGraph An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image
13. CVPR 2026GeoBridge A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text
14. CVPR 2026GlyphPrinter Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering
15. CVPR 2026GrOCE Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models
16. CVPR 2026JANUS A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution
17. CVPR 2026Learning complete and explainable visual representations from itemized text supervision
18. CVPR 2026Learning Effective Sign Features without Text for Gloss-free Sign Language
19. CVPR 2026Mostly Text Smart Visuals Asymmetric Text-Visual Pruning for Large Vision-Language
20. CVPR 2026MotionHiFlow Text-to-Motion via Hierarchical Flow Matching
21. CVPR 2026Multimodal RewardBench 2 Evaluating Omni Reward Models for Interleaved Text
22. CVPR 2026OctoT2I A Self-Evolving Agentic Text-to-Image Router
23. CVPR 2026ParTY Part-Guidance for Expressive Text-to-Motion Synthesis
24. CVPR 2026Premier Personalized Preference Modulation with Learnable User Embedding in Text-to-Image
25. CVPR 2026Pressure2Motion Hierarchical Human Motion Reconstruction from Ground Pressure with Text
26. CVPR 2026Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification
27. CVPR 2026PureCC Pure Learning for Text-to-Image Concept Customization
28. CVPR 2026PV-Ground Text-Guided Point-Voxel Interaction for 3D Visual Grounding
29. CVPR 2026R2TUA Reconstruction-residual Based Targeted and Untargeted Attack Against Text-Image Person
30. CVPR 2026Residual Decoder Adapter ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering
31. CVPR 2026Restore Text First Enhance Image Later Two-Stage Scene Text Image
32. CVPR 2026RI-Mamba Rotation-Invariant Mamba for Robust Text-to-Shape Retrieval
33. CVPR 2026Robust Remote Sensing Image-Text Retrieval with Noisy Correspondence
34. CVPR 2026SAVE Speech-Aware Video Representation Learning for Video-Text Retrieval
35. CVPR 2026Seeing is Improving Visual Feedback for Iterative Text Layout Refinement
36. CVPR 2026Selectively Extracting and Injecting Visual Attributes into Text-to-Image Models
37. CVPR 2026SkyReels-Text Fine-Grained Font-Controllable Text Editing for Poster Design
38. CVPR 2026Talk2Move Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes
39. CVPR 2026TANGO Text-Anchored Guided Optimization for Robust Fine-tuning Vision-Language Models under
40. CVPR 2026TeHOR Text-Guided 3D Human and Object Reconstruction with Textures
41. CVPR 2026Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
42. CVPR 2026TextPecker Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering
43. CVPR 2026Texvent Asynchronous Event Data Simulation via Text Prompt
44. CVPR 2026TIACam Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking
45. CVPR 2026TINA Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models
46. CVPR 2026Toward Early Quality Assessment of Text-to-Image Diffusion Models
47. CVPR 2026Towards Training-free Scene Text Editing
48. CVPR 2026Vinedresser3D Towards Agentic Text-guided 3D Editing
49. CVPR 2026Vision-Speech Models Teaching Speech Models to Converse about Images
50. CVPR 2026Whats Wrong with Synthetic Data for Scene Text Recognition A

常见问题

2023–2026 年四大会议一共有多少篇语音合成论文？

共 621 篇，按年份分别是 2023 年 125 篇、2024 年 145 篇、2025 年 151 篇、2026 年 200 篇。

NeurIPS 2026 有多少篇语音合成论文？

NeurIPS 2026 有 67 篇语音合成论文，上一届是 45 篇。

ICLR 2026 有多少篇语音合成论文？

ICLR 2026 有 43 篇语音合成论文，上一届是 32 篇。

ICML 2026 有多少篇语音合成论文？

ICML 2026 有 36 篇语音合成论文，上一届是 16 篇。

CVPR 2026 有多少篇语音合成论文？

CVPR 2026 有 54 篇语音合成论文，上一届是 58 篇。

哪个会议的语音合成论文最多？

NeurIPS，2023–2026 年共 204 篇。