语音合成论文趋势 2023–2026

TTS 与声码器

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 621 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

语音合成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202354222623125
202438262160145
202545321658151
202667433654200

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

全部语音合成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 200 篇，第 4 / 4 页

  1. NeurIPS 2026Is Text All You Need? Text as a Universal Information Bottleneck for Speech LLMs
  2. NeurIPS 2026Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech
  3. NeurIPS 2026Language Denoising Objectives Extend the Value of Limited Data
  4. NeurIPS 2026LensCT: Fine-Grained AI-Involved Text Detection via Temporal-Hierarchical Tomograms of LLM Internals
  5. NeurIPS 2026LibriBrain100: One Hundred Hours of Broad and Deep MEG Data for Neural Speech Decoding at Scale
  6. NeurIPS 2026LLM Flow Processes for Text-Conditioned Regression
  7. NeurIPS 2026Log-Likelihood, Simpson’s Paradox, and the Detection of Machine-Generated Text
  8. NeurIPS 2026Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension
  9. NeurIPS 2026Majority-of-Three is an Optimal PAC Learner
  10. NeurIPS 2026Making Open-Source Text LLM Watermarks Durable Against Merging
  11. NeurIPS 2026MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments
  12. NeurIPS 2026Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM
  13. NeurIPS 2026MOSAIC: Concept Bottlenecks via Text-Anchored Optimal Transport
  14. NeurIPS 2026MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation
  15. NeurIPS 2026NeuroFaith: Evaluating Mechanistic Faithfulness of LLM Free Text Self-Explanation at the Concept Level
  16. NeurIPS 2026NeuroInk: Retinomorphic Spiking Sequence Modeling for Handwritten Text Recognition
  17. NeurIPS 2026No Model Required: Text Entropy Rate Filtering Prevents Iterative Fine-Tuning Collapse
  18. NeurIPS 2026On Length Bias in EEG-to-Text Decoding
  19. NeurIPS 2026ORCA: Hunting Compositional Failures in Text-to-Image Diffusion
  20. NeurIPS 2026PATH: A Dual Perspective for High-quality Text-attributed Graph Learning
  21. NeurIPS 2026Permute-then-Adapt: Weak-to-Strong Contrastive Image--Text Adaptation
  22. NeurIPS 2026Pref-DetectGPT: Unveiling Machine-Generated Text via Preference-Aware Curvature Measurement
  23. NeurIPS 2026Pretraining Data Statistics Shape the Phases of Learning Entity Comparison in Language Models
  24. NeurIPS 2026Prior Text-Informed Gate Attention Framework for Multimodal Psychiatric Disorder Diagnosis
  25. NeurIPS 2026PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
  26. NeurIPS 2026Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?
  27. NeurIPS 2026Rep2Text: Decoding Full Text from a Single LLM Token Representation
  28. NeurIPS 2026Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder
  29. NeurIPS 2026Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and Large Language Models
  30. NeurIPS 2026RobustStress: Stress-Testing AI-Generated Text Detectors under Gradual Perturbations
  31. NeurIPS 2026Say the Same, Act Differently: Text-Orthogonal Action Subspaces in Reasoning Vision-Language-Action Models
  32. NeurIPS 2026Seeing but Not Detecting: Privacy-Preserving Scene Text Attack via Hybrid Adversarial Policy Learning
  33. NeurIPS 2026Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial Animation
  34. NeurIPS 2026SENSE: Semantic Neural Speech Synthesis from Brain Dynamics via Spatial Graph Encoding
  35. NeurIPS 2026She Performs Your Voice: A Unified Speech and Dance Motion Model
  36. NeurIPS 2026SMASH: Probing Speech Recognition Robustness via Semantically Targeted Bit Flips
  37. NeurIPS 2026Speech Tokenizers are Vulnerable: Transferable Semantic Attack and Robust Tokenizer
  38. NeurIPS 2026TED: Text-Axis Evidence Decomposition for Prompted Anomaly Localization
  39. NeurIPS 2026Text-to-CAD Evaluation with CADTests
  40. NeurIPS 2026TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs
  41. NeurIPS 2026TriBet: Relative E-values for Online Machine-generated Text Detection
  42. NeurIPS 2026TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization
  43. NeurIPS 2026Uncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM–GNN Synergy
  44. NeurIPS 2026View-Spectral Reconciliation Learning for Text-based Multispectral Aerial–Ground Person Re-Identification
  45. NeurIPS 2026VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries
  46. NeurIPS 2026Visual Text Compression as Measure Transport
  47. NeurIPS 2026ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing
  48. NeurIPS 2026Viverra: Text-to-Code with Guarantees
  49. NeurIPS 2026WAXAL: A Large-Scale Multilingual African Language Speech Corpus
  50. NeurIPS 2026When Language Overrules: Revealing Text Dominance in Multimodal Large 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 查语音合成在 NeurIPS 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": "text-to-speech"}

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合成论文？
共 621 篇，按年份分别是 2023 年 125 篇、2024 年 145 篇、2025 年 151 篇、2026 年 200 篇。
NeurIPS 2026 有多少篇语音合成论文？
NeurIPS 2026 有 67 篇语音合成论文，上一届是 45 篇。
ICLR 2026 有多少篇语音合成论文？
ICLR 2026 有 43 篇语音合成论文，上一届是 32 篇。
ICML 2026 有多少篇语音合成论文？
ICML 2026 有 36 篇语音合成论文，上一届是 16 篇。
CVPR 2026 有多少篇语音合成论文？
CVPR 2026 有 54 篇语音合成论文，上一届是 58 篇。
哪个会议的语音合成论文最多？
NeurIPS，2023–2026 年共 204 篇。

「语音与音频」下的其他主题