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 8 / 11 页

  1. ICML 2025Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines
  2. ICML 2025Delta Decompression for MoE-based LLMs Compression
  3. ICML 2025Dendritic Localized Learning: Toward Biologically Plausible Algorithm
  4. ICML 2025DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis
  5. ICML 2025Efficiently Serving Large Multimodal Models Using EPD Disaggregation
  6. ICML 2025Emotional Face-to-Speech
  7. ICML 2025ETTA: Elucidating the Design Space of Text-to-Audio Models
  8. ICML 2025Faster and Stronger: When ANN-SNN Conversion Meets Parallel Spiking Calculation
  9. ICML 2025FLAM: Frame-Wise Language-Audio Modeling
  10. ICML 2025Fleet of Agents: Coordinated Problem Solving with Large Language Models
  11. ICML 2025Flexible and Efficient Grammar-Constrained Decoding
  12. ICML 2025Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM
  13. ICML 2025From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning
  14. ICML 2025Generalized Venn and Venn-Abers Calibration with Applications in Conformal Prediction
  15. ICML 2025Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction
  16. ICML 2025Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates
  17. ICML 2025Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs
  18. ICML 2025High-Fidelity Simultaneous Speech-To-Speech Translation
  19. ICML 2025Implicit Riemannian Optimism with Applications to Min-Max Problems
  20. ICML 2025KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
  21. ICML 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing
  22. ICML 2025Learn Singularly Perturbed Solutions via Homotopy Dynamics
  23. ICML 2025Learning from others' mistakes: Finetuning machine translation models with span-level error annotations
  24. ICML 2025Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive Supervision
  25. ICML 2025Learning with Expected Signatures: Theory and Applications
  26. ICML 2025Long-Form Speech Generation with Spoken Language Models
  27. ICML 2025Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic
  28. ICML 2025MATS: An Audio Language Model under Text-only Supervision
  29. ICML 2025MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-text Decoding
  30. ICML 2025MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition
  31. ICML 2025Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding
  32. ICML 2025MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners
  33. ICML 2025NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
  34. ICML 2025OmniAudio: Generating Spatial Audio from 360-Degree Video
  35. ICML 2025One Wave To Explain Them All: A Unifying Perspective On Feature Attribution
  36. ICML 2025Otter: Generating Tests from Issues to Validate SWE Patches
  37. ICML 2025Overcoming Non-monotonicity in Transducer-based Streaming Generation
  38. ICML 2025OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models
  39. ICML 2025PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations
  40. ICML 2025Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion
  41. ICML 2025Policy Filtration for RLHF to Mitigate Noise in Reward Models
  42. ICML 2025Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications
  43. ICML 2025QuanONet: Quantum Neural Operator with Application to Differential Equation
  44. ICML 2025Reducing Tool Hallucination via Reliability Alignment
  45. ICML 2025RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior
  46. ICML 2025Rethink GraphODE Generalization within Coupled Dynamical System
  47. ICML 2025ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networks
  48. ICML 2025SING: Spatial Context in Large Language Model for Next-Gen Wearables
  49. ICML 2025Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems
  50. ICML 2025Steering Protein Language 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