语音合成论文趋势 2023–2026

TTS 与声码器

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 621 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

语音合成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202354222623125
202438262160145
202545321658151
202667433654200

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

全部语音合成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 621 篇，第 11 / 13 页

  1. CVPR 2023CodeTalker: Speech-Driven 3D Facial Animation With Discrete Motion Prior
  2. CVPR 2023DeepSolo: Let Transformer Decoder With Explicit Points Solo for Text Spotting
  3. CVPR 2023Diffusion-SDF: Text-To-Shape via Voxelized Diffusion
  4. CVPR 2023Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning Network
  5. CVPR 2023Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting
  6. CVPR 2023Improving Image Recognition by Retrieving From Web-Scale Image-Text Data
  7. CVPR 2023Learning Semantic Relationship Among Instances for Image-Text Matching
  8. CVPR 2023Multi-Concept Customization of Text-to-Image Diffusion
  9. CVPR 2023Position-Guided Text Prompt for Vision-Language Pre-Training
  10. CVPR 2023QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation
  11. CVPR 2023ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration
  12. CVPR 2023SceneTrilogy: On Human Scene-Sketch and Its Complementarity With Photo and Text
  13. CVPR 2023Self-Supervised Implicit Glyph Attention for Text Recognition
  14. CVPR 2023Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style
  15. CVPR 2023Text With Knowledge Graph Augmented Transformer for Video Captioning
  16. CVPR 2023Text2Scene: Text-Driven Indoor Scene Stylization With Part-Aware Details
  17. CVPR 2023Turning a CLIP Model Into a Scene Text Detector
  18. CVPR 2023Uncurated Image-Text Datasets: Shedding Light on Demographic Bias
  19. CVPR 2023VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models
  20. ICLR 2023A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification
  21. ICLR 2023An efficient encoder-decoder architecture with top-down attention for speech separation
  22. ICLR 2023Bag of Tricks for Unsupervised Text-to-Speech
  23. ICLR 2023Causal Estimation for Text Data with (Apparent) Overlap Violations
  24. ICLR 2023CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos
  25. ICLR 2023Continuous pseudo-labeling from the start
  26. ICLR 2023Copy is All You Need
  27. ICLR 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness
  28. ICLR 2023In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations
  29. ICLR 2023Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance
  30. ICLR 2023Learning on Large-scale Text-attributed Graphs via Variational Inference
  31. ICLR 2023Linear Connectivity Reveals Generalization Strategies
  32. ICLR 2023Linearly Mapping from Image to Text Space
  33. ICLR 2023NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis
  34. ICLR 2023Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation
  35. ICLR 2023Quantifying Memorization Across Neural Language Models
  36. ICLR 2023Revisiting the Entropy Semiring for Neural Speech Recognition
  37. ICLR 2023SMART: Sentences as Basic Units for Text Evaluation
  38. ICLR 2023Spiking Convolutional Neural Networks for Text Classification
  39. ICLR 2023Stay Moral and Explore: Learn to Behave Morally in Text-based Games
  40. ICLR 2023Text Summarization with Oracle Expectation
  41. ICLR 2023TextShield: Beyond Successfully Detecting Adversarial Sentences in text classification
  42. ICML 2023A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
  43. ICML 2023A Unifying Framework to the Analysis of Interaction Methods using Synergy Functions
  44. ICML 2023Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
  45. ICML 2023CLIPood: Generalizing CLIP to Out-of-Distributions
  46. ICML 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
  47. ICML 2023Distributed Stochastic Gradient Descent: Nonconvexity, Nonsmoothness, and Convergence to Local Minima
  48. ICML 2023Formalizing Preferences Over Runtime Distributions
  49. ICML 2023From Adaptive Query Release to Machine Unlearning
  50. ICML 2023From Perception to Programs: Regularize, Overparameterize, and Amortize

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查语音合成在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "text-to-speech"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「语音与音频」下的其他主题