语音识别论文趋势 2023–2026

ASR

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 230 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

语音识别论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202341465175
202413862855
202522751650
202616781950

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

全部语音识别论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 230 篇，第 2 / 5 页

  1. CVPR 20255%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks
  2. CVPR 2025Action Detail Matters: Refining Video Recognition with Local Action Queries
  3. CVPR 2025CryptoFace: End-to-End Encrypted Face Recognition
  4. CVPR 2025Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion
  5. CVPR 2025Enhanced Visual-Semantic Interaction with Tailored Prompts for Pedestrian Attribute Recognition
  6. CVPR 2025EZSR: Event-based Zero-Shot Recognition
  7. CVPR 2025ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images
  8. CVPR 2025GIF: Generative Inspiration for Face Recognition at Scale
  9. CVPR 2025LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale
  10. CVPR 2025Mamba-Adaptor: State Space Model Adaptor for Visual Recognition
  11. CVPR 2025MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning
  12. CVPR 2025Multi-Modal Aerial-Ground Cross-View Place Recognition with Neural ODEs
  13. CVPR 2025On Denoising Walking Videos for Gait Recognition
  14. CVPR 2025On the Generalization of Handwritten Text Recognition Models
  15. CVPR 2025Recognition-Synergistic Scene Text Editing
  16. CVPR 2025Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
  17. ICLR 2025Context-aware Dynamic Pruning for Speech Foundation Models
  18. ICLR 2025CR-CTC: Consistency regularization on CTC for improved speech recognition
  19. ICLR 2025Improving Semantic Understanding in Speech Language Models via Brain-tuning
  20. ICLR 2025Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions
  21. ICLR 2025Scaling Speech-Text Pre-training with Synthetic Interleaved Data
  22. ICLR 2025Speech Robust Bench: A Robustness Benchmark For Speech Recognition
  23. ICLR 2025T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via Multitask Learning
  24. ICML 2025Gamma Distribution PCA-Enhanced Feature Learning for Angle-Robust SAR Target Recognition
  25. ICML 2025OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models
  26. ICML 2025Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in sEMG Analysis
  27. ICML 2025SING: Spatial Context in Large Language Model for Next-Gen Wearables
  28. ICML 2025Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems
  29. NeurIPS 2025Adaptive Re-calibration Learning for Balanced Multimodal Intention Recognition
  30. NeurIPS 2025BlockDecoder: Boosting ASR Decoders with Context and Merger Modules
  31. NeurIPS 2025DataSIR: A Benchmark Dataset for Sensitive Information Recognition
  32. NeurIPS 2025Deep Tree Tensor Networks
  33. NeurIPS 2025Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition
  34. NeurIPS 2025E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models
  35. NeurIPS 2025Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers, and Gradient Clipping
  36. NeurIPS 2025EuroSpeech: A Multilingual Speech Corpus
  37. NeurIPS 2025FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition
  38. NeurIPS 2025L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery
  39. NeurIPS 2025Long-Tailed Recognition via Information-Preservable Two-Stage Learning
  40. NeurIPS 2025Long-tailed Recognition with Model Rebalancing
  41. NeurIPS 2025MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition
  42. NeurIPS 2025MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition
  43. NeurIPS 2025Multi-head Temporal Latent Attention
  44. NeurIPS 2025Objective Soups: Multilingual Multi-Task Modeling for Speech Processing
  45. NeurIPS 2025PASS: Path-selective State Space Model for Event-based Recognition
  46. NeurIPS 2025Preference-Based Dynamic Ranking Structure Recognition
  47. NeurIPS 2025Reading Recognition in the Wild
  48. NeurIPS 2025RESPIN-S1.0: A read speech corpus of 10000+ hours in dialects of nine Indian Languages
  49. NeurIPS 2025SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors
  50. NeurIPS 2025WolBanking77: Wolof Banking Speech Intent Classification Dataset

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 查语音识别在 CVPR 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": "speech-recognition"}

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识别论文？
共 230 篇，按年份分别是 2023 年 75 篇、2024 年 55 篇、2025 年 50 篇、2026 年 50 篇。
NeurIPS 2026 有多少篇语音识别论文？
NeurIPS 2026 有 16 篇语音识别论文，上一届是 22 篇。
ICLR 2026 有多少篇语音识别论文？
ICLR 2026 有 7 篇语音识别论文，上一届是 7 篇。
ICML 2026 有多少篇语音识别论文？
ICML 2026 有 8 篇语音识别论文，上一届是 5 篇。
CVPR 2026 有多少篇语音识别论文？
CVPR 2026 有 19 篇语音识别论文，上一届是 16 篇。
哪个会议的语音识别论文最多？
CVPR，2023–2026 年共 114 篇。

「语音与音频」下的其他主题