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 505 篇，第 7 / 11 页

  1. ICLR 2025TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation
  2. ICLR 2025TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction
  3. ICLR 2025TeaserGen: Generating Teasers for Long Documentaries
  4. ICLR 2025Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness
  5. ICLR 2025TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes
  6. ICLR 2025TexTailor: Customized Text-aligned Texturing via Effective Resampling
  7. ICLR 2025The impact of allocation strategies in subset learning on the expressive power of neural networks
  8. ICLR 2025Theory, Analysis, and Best Practices for Sigmoid Self-Attention
  9. ICLR 2025ThermalGaussian: Thermal 3D Gaussian Splatting
  10. ICLR 2025TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
  11. ICLR 2025ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts
  12. ICLR 2025Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial Recordings
  13. ICLR 2025Towards Unbiased Learning in Semi-Supervised Semantic Segmentation
  14. ICLR 2025Towards Unified Human Motion-Language Understanding via Sparse Interpretable Characterization
  15. ICLR 2025Track-On: Transformer-based Online Point Tracking with Memory
  16. ICLR 2025Training-Free Dataset Pruning for Instance Segmentation
  17. ICLR 2025Uncertainty modeling for fine-tuned implicit functions
  18. ICLR 2025Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection
  19. ICLR 2025UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization
  20. ICLR 2025UniCoTT: A Unified Framework for Structural Chain-of-Thought Distillation
  21. ICLR 2025Union-over-Intersections: Object Detection beyond Winner-Takes-All
  22. ICLR 2025UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation
  23. ICLR 2025Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model
  24. ICLR 2025UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate
  25. ICLR 2025Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement
  26. ICLR 2025Vision-LSTM: xLSTM as Generic Vision Backbone
  27. ICLR 2025Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
  28. ICLR 2025Visual Agents as Fast and Slow Thinkers
  29. ICLR 2025W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models
  30. ICLR 2025Watermark Anything With Localized Messages
  31. ICLR 2025WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
  32. ICLR 2025Wayward Concepts In Multimodal Models
  33. ICLR 2025What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
  34. ICLR 2025X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
  35. ICLR 2025X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention
  36. ICML 2025A Reasoning-Based Approach to Cryptic Crossword Clue Solving
  37. ICML 2025A Variational Framework for Improving Naturalness in Generative Spoken Language Models
  38. ICML 2025Active Evaluation Acquisition for Efficient LLM Benchmarking
  39. ICML 2025Adaptive Elicitation of Latent Information Using Natural Language
  40. ICML 2025Aligning Spoken Dialogue Models from User Interactions
  41. ICML 2025ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling
  42. ICML 2025AnalogGenie-Lite: Enhancing Scalability and Precision in Circuit Topology Discovery through Lightweight Graph Modeling
  43. ICML 2025Are Large Language Models Ready for Multi-Turn Tabular Data Analysis?
  44. ICML 2025ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior
  45. ICML 2025Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
  46. ICML 2025BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models
  47. ICML 2025Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation
  48. ICML 2025Compressed and distributed least-squares regression: convergence rates with applications to federated learning
  49. ICML 2025CoSER: Coordinating LLM-Based Persona Simulation of Established Roles
  50. ICML 2025Deep Neural Cellular Potts Models

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