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 27 / 35 页

  1. NeurIPS 2025SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation
  2. NeurIPS 2025SAO-Instruct: Free-form Audio Editing using Natural Language Instructions
  3. NeurIPS 2025SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing
  4. NeurIPS 2025Semi-supervised Vertex Hunting, with Applications in Network and Text Analysis
  5. NeurIPS 2025SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors
  6. NeurIPS 2025Siegel Neural Networks
  7. NeurIPS 2025SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation
  8. NeurIPS 2025SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement
  9. NeurIPS 2025SpaceServe: Spatial Multiplexing of Complementary Encoders and Decoders for Multimodal LLMs
  10. NeurIPS 2025Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching
  11. NeurIPS 2025SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset
  12. NeurIPS 2025TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling
  13. NeurIPS 2025TAPIP3D: Tracking Any Point in Persistent 3D Geometry
  14. NeurIPS 2025Target Speaker Extraction through Comparing Noisy Positive and Negative Audio Enrollments
  15. NeurIPS 2025The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
  16. NeurIPS 2025The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
  17. NeurIPS 2025The Omni-Expert: A Computationally Efficient Approach to Achieve a Mixture of Experts in a Single Expert Model
  18. NeurIPS 2025Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech Decoding
  19. NeurIPS 2025Towards Realistic Earth-Observation Constellation Scheduling: Benchmark and Methodology
  20. NeurIPS 2025Ultra-high Resolution Watermarking Framework Resistant to Extreme Cropping and Scaling
  21. NeurIPS 2025Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
  22. NeurIPS 2025VASA-3D: Lifelike Audio-Driven Gaussian Head Avatars from a Single Image
  23. NeurIPS 2025VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
  24. NeurIPS 2025VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model
  25. NeurIPS 2025Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM
  26. NeurIPS 2025Why Playing Against Diverse and Challenging Opponents Speeds Up Coevolution: A Theoretical Analysis on Combinatorial Games
  27. NeurIPS 2025Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis
  28. NeurIPS 2025ZeroSep: Separate Anything in Audio with Zero Training
  29. CVPR 2024A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition
  30. CVPR 2024AV-RIR: Audio-Visual Room Impulse Response Estimation
  31. CVPR 2024AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation
  32. CVPR 2024AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection
  33. CVPR 2024Benchmarking Audio Visual Segmentation for Long-Untrimmed Videos
  34. CVPR 2024Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model
  35. CVPR 2024ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis
  36. CVPR 2024Cyclic Learning for Binaural Audio Generation and Localization
  37. CVPR 2024DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction
  38. CVPR 2024DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation
  39. CVPR 2024DiVAS: Video and Audio Synchronization with Dynamic Frame Rates
  40. CVPR 2024Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
  41. CVPR 2024EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
  42. CVPR 2024Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion
  43. CVPR 2024ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations
  44. CVPR 2024FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio
  45. CVPR 2024Faces that Speak: Jointly Synthesising Talking Face and Speech from Text
  46. CVPR 2024FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models
  47. CVPR 2024From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations
  48. CVPR 2024Functional Diffusion
  49. CVPR 2024Garment Recovery with Shape and Deformation Priors
  50. CVPR 2024Hearing Anything Anywhere

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