应用 · speech and audio论文趋势 2023–2026

应用方向：speech_and_audio

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,722 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

应用 · speech and audio论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202331273227117
2024531285244277
2025982927243505
202615345117148823

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

全部应用 · speech and audio论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,722 篇，第 20 / 35 页

  1. ICLR 2025Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping
  2. ICLR 2025Gaussian Splatting Lucas-Kanade
  3. ICLR 2025Gaussian-Based Instance-Adaptive Intensity Modeling for Point-Supervised Facial Expression Spotting
  4. ICLR 2025GenDataAgent: On-the-fly Dataset Augmentation with Synthetic Data
  5. ICLR 2025Generalized Video Moment Retrieval
  6. ICLR 2025GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling
  7. ICLR 2025Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation
  8. ICLR 2025GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering
  9. ICLR 2025GLOMA: Global Video Text Spotting with Morphological Association
  10. ICLR 2025Graph-Guided Scene Reconstruction from Images with 3D Gaussian Splatting
  11. ICLR 2025Grounding Multimodal Large Language Model in GUI World
  12. ICLR 2025GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting
  13. ICLR 2025GSE: Group-wise Sparse and Explainable Adversarial Attacks
  14. ICLR 2025HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR
  15. ICLR 2025HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis
  16. ICLR 2025Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
  17. ICLR 2025High-dimension Prototype is a Better Incremental Object Detection Learner
  18. ICLR 2025High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation
  19. ICLR 2025HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction
  20. ICLR 2025How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings
  21. ICLR 2025HQGS: High-Quality Novel View Synthesis with Gaussian Splatting in Degraded Scenes
  22. ICLR 2025I Can Hear You: Selective Robust Training for Deepfake Audio Detection
  23. ICLR 2025IDInit: A Universal and Stable Initialization Method for Neural Network Training
  24. ICLR 2025IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATION
  25. ICLR 2025Image and Video Tokenization with Binary Spherical Quantization
  26. ICLR 2025IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning
  27. ICLR 2025ImDy: Human Inverse Dynamics from Imitated Observations
  28. ICLR 2025Implicit Neural Surface Deformation with Explicit Velocity Fields
  29. ICLR 2025Improving Language Model Distillation through Hidden State Matching
  30. ICLR 2025Improving Semantic Understanding in Speech Language Models via Brain-tuning
  31. ICLR 2025Improving Unsupervised Constituency Parsing via Maximizing Semantic Information
  32. ICLR 2025Influence-Guided Diffusion for Dataset Distillation
  33. ICLR 2025InfoGS: Efficient Structure-Aware 3D Gaussians via Lightweight Information Shaping
  34. ICLR 2025InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting
  35. ICLR 2025InstaRevive: One-Step Image Enhancement via Dynamic Score Matching
  36. ICLR 2025Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios
  37. ICLR 2025Interpretable Vision-Language Survival Analysis with Ordinal Inductive Bias for Computational Pathology
  38. ICLR 2025Inverse decision-making using neural amortized Bayesian actors
  39. ICLR 2025Inverse Rendering using Multi-Bounce Path Tracing and Reservoir Sampling
  40. ICLR 2025Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning
  41. ICLR 2025Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity
  42. ICLR 2025Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding
  43. ICLR 2025Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution
  44. ICLR 2025Kronecker Mask and Interpretive Prompts are Language-Action Video Learners
  45. ICLR 2025L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and Enhancement
  46. ICLR 2025Language-Assisted Feature Transformation for Anomaly Detection
  47. ICLR 2025Latent Radiance Fields with 3D-aware 2D Representations
  48. ICLR 2025Learning Clustering-based Prototypes for Compositional Zero-Shot Learning
  49. ICLR 2025Learning Evolving Tools for Large Language Models
  50. ICLR 2025Learning Fine-Grained Representations through Textual Token Disentanglement in Composed Video Retrieval

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 查应用 · speech and audio在 ICLR 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": "app-speech-and-audio"}

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应用 · speech and audio论文？
共 1,722 篇，按年份分别是 2023 年 117 篇、2024 年 277 篇、2025 年 505 篇、2026 年 823 篇。
NeurIPS 2026 有多少篇应用 · speech and audio论文？
NeurIPS 2026 有 153 篇应用 · speech and audio论文，上一届是 98 篇。
ICLR 2026 有多少篇应用 · speech and audio论文？
ICLR 2026 有 451 篇应用 · speech and audio论文，上一届是 292 篇。
ICML 2026 有多少篇应用 · speech and audio论文？
ICML 2026 有 171 篇应用 · speech and audio论文，上一届是 72 篇。
CVPR 2026 有多少篇应用 · speech and audio论文？
CVPR 2026 有 48 篇应用 · speech and audio论文，上一届是 43 篇。
哪个会议的应用 · speech and audio论文最多？
ICLR，2023–2026 年共 898 篇。

「应用领域」下的其他主题