应用 · speech and audio论文趋势 2023–2026

主要结论

• 应用 · speech and audio论文从 2023 年的 117 篇增长到 2026 年的 823 篇，三年间扩大到约 7.0 倍。
• ICLR 是发应用 · speech and audio论文最多的会议，2023–2026 年共 898 篇，占四个会议总量的 52%。
• 交叉方向里涨得最快的是应用 · computer vision：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 292 篇。
• 在「应用领域」的 10 个主题里，它的 2026 年论文数排第 3；同组增长最快的应用 · health medicine是 61 倍，应用 · speech and audio是 7.0 倍。

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

• NeurIPS 2026(Strongly) Replicable Distribution Testers imply High Probability Distribution Testers
• ICML 2026(Be Cautious!) Bio-Foundation Models Are Not Yet Robust to Biologically Plausible Perturbations and ML Transformations
• ICLR 2026A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features
• CVPR 2026Globscope Toward a Global View of the Loss Landscape
• NeurIPS 2025AHa-Bench: Benchmarking Audio Hallucinations in Large Audio-Language Models
• ICML 2025A Variational Framework for Improving Naturalness in Generative Spoken Language Models
• ICLR 2025A Multiscale Frequency Domain Causal Framework for Enhanced Pathological Analysis
• CVPR 2025Blurred LiDAR for Sharper 3D: Robust Handheld 3D Scanning with Diffuse LiDAR and RGB
• NeurIPS 2024Acoustic Volume Rendering for Neural Impulse Response Fields
• ICML 2024$\bf{\Phi}_\textrm{Flow}$: Differentiable Simulations for PyTorch, TensorFlow and Jax
• ICLR 2024Dynamic Neural Response Tuning
• CVPR 2024DiVAS: Video and Audio Synchronization with Dynamic Frame Rates
• NeurIPS 2023[Re] Exploring the Role of Grammar and Word Choice in Bias Toward African American English (AAE) in Hate Speech Classification
• ICML 2023Accuracy on the Curve: On the Nonlinear Correlation of ML Performance Between Data Subpopulations
• ICLR 2023An efficient encoder-decoder architecture with top-down attention for speech separation
• CVPR 20233D Line Mapping Revisited
• NeurIPS 2026Approximate Matrix–Vectors Under a Bounded $\ell_1$ Assumption and Applications to Kernel Matrices
• ICML 2026AudioChat: Unified Audio Storytelling, Editing, and Understanding with Transfusion Forcing
• ICLR 2026A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models
• CVPR 2026Hierarchical Codec Diffusion for Video-to-Speech Generation

全部应用 · speech and audio论文

共 171 篇，第 3 / 4 页

101. ICML 2026On the Infinite Width and Depth Limits of Predictive Coding Networks
102. ICML 2026On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective
103. ICML 2026Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification
104. ICML 2026Optimizing Diversity and Quality through Base-Aligned Model Collaboration
105. ICML 2026PHALAR: Phasors for Learned Musical Audio Representations
106. ICML 2026PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMs
107. ICML 2026Physically-Guided Data-Space Rectified Flow for Precipitation Nowcasting
108. ICML 2026Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training
109. ICML 2026Plan Then Action: High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
110. ICML 2026Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration
111. ICML 2026Proximal Splitting Methods for Hybrid Differentiable Models
112. ICML 2026Quaternion Self-Attention with Shared Scores
113. ICML 2026Query-Based Asymmetric Modeling with Decoupled Input–Output Rates for Speech Restoration
114. ICML 2026Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains
115. ICML 2026Real-World Unsupervised Models Generalize to Predict Brain Responses to Out-of-Distribution Stimuli
116. ICML 2026ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models
117. ICML 2026Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue
118. ICML 2026Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference
119. ICML 2026Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement
120. ICML 2026REST: Diffusion-based Real-time End-to-end Streaming Talking Head Generation via ID-Context Caching and Asynchronous Streaming Distillation
121. ICML 2026Rethink the Role of Neural Decoders in Quantum Error Correction
122. ICML 2026Rethinking Attention in Spiking Transformers: Overcoming Density Bias with Set Similarity
123. ICML 2026Rethinking Code Complexity Through the Lens of Large Language Models
124. ICML 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
125. ICML 2026Rewiring Experts on the Fly: Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert Models
126. ICML 2026Safe and Scalable Web Agent Learning via Recreated Websites
127. ICML 2026SAM Audio: Segment Anything in Audio
128. ICML 2026Scaling Behavior in Model Fine-tuning for Audio DeepFake Detection
129. ICML 2026Scaling Small Agents Through Strategy Auctions
130. ICML 2026Scaling Transformers for End-to-End Discrete Audio Tokenization
131. ICML 2026Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment
132. ICML 2026SENDAI: A Hierarchical Sparse-measurement, EfficieNt Data AssImilation Framework
133. ICML 2026Simple Algorithms for Bad Triangle Transversals with Applications to Correlation Clustering
134. ICML 2026Simultaneous Speech-to-Speech Translation Without Aligned Data
135. ICML 2026SmoothSpike: Spiking Transformer with Learnable Hadamard Transformation
136. ICML 2026SoftMatcha 2: A Fast and Soft Pattern Matcher for Trillion-Scale Corpora
137. ICML 2026SONAR: Spectral‑Contrastive Audio Residuals for Generalizable Deepfake Detection
138. ICML 2026SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
139. ICML 2026Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech
140. ICML 2026SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations
141. ICML 2026Speech-Audio Compositional Attacks on Multimodal LLMs and Their Defense with SALMONN-Guard
142. ICML 2026SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
143. ICML 2026Spherical Procrustes Alignment for Reliable Medical Audio Diagnosis
144. ICML 2026SpikingLM: Towards Fully Spiking Language Model
145. ICML 2026STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation
146. ICML 2026STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits
147. ICML 2026StormInsight: Hierarchical Environmental Forcing and Vertical Coupling for Weather System Evolution
148. ICML 2026SWE-IF: Aligning Code Evaluation with Human Preference
149. ICML 2026TG-RAG: A Retrieval-Augmented Framework for Reasoning Guidance in Specialized Domains
150. ICML 2026The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning

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。