Speech Recognition papers, 2023–2026

Key findings

• Speech Recognition fell from 75 papers in 2023 to 50 in 2026, so interest is cooling.
• CVPR publishes the most Speech Recognition work: 114 papers from 2023 to 2026, 50% of the four-venue total.
• The fastest-growing overlap is with Applications · speech and audio: papers tagged with both rose from 13 in 2023 to 15 in 2026.
• Among the 5 topics under Audio and Speech, it ranks #5 by 2026 paper count; the fastest grower in the group, Audio Generation, is up 4.3x versus 0.7x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition
• ICML 2026Shortcut-Resistant CAM Distillation for Long-Tailed Recognition
• ICLR 2026CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition
• CVPR 2026CLEX Complementary Label Exchange Learning for Noisy Facial Expression Recognition
• NeurIPS 2025EuroSpeech: A Multilingual Speech Corpus
• ICML 2025OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models
• ICLR 2025Speech Robust Bench: A Robustness Benchmark For Speech Recognition
• CVPR 2025CryptoFace: End-to-End Encrypted Face Recognition
• NeurIPS 2024[Re] CUDA: Curriculum of Data Augmentation for Long‐tailed Recognition
• ICML 2024Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition
• ICLR 2024It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
• CVPR 2024From Coarse to Fine-Grained Open-Set Recognition
• NeurIPS 2023Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition
• ICML 2023Robust Speech Recognition via Large-Scale Weak Supervision
• ICLR 2023Continuous pseudo-labeling from the start
• CVPR 2023BioNet: A Biologically-Inspired Network for Face Recognition
• NeurIPS 2026PIGRAM: An Interpretable Patch--Motif Interaction Grammar for Protein--Nucleic-Acid Recognition
• ICML 2026Context-free Recognition with Transformers
• ICLR 2026Confident and Adaptive Generative Speech Recognition via Conformal Risk Control
• CVPR 2026DialogueVPR Towards Conversational Visual Place Recognition

All Speech Recognition papers

230 papers, page 5 of 5

201. CVPR 2023Transformer-Based Unified Recognition of Two Hands Manipulating Objects
202. CVPR 2023Unified Keypoint-Based Action Recognition Framework via Structured Keypoint Pooling
203. CVPR 2023Use Your Head: Improving Long-Tail Video Recognition
204. CVPR 2023Visual Recognition by Request
205. CVPR 2023Visual Recognition-Driven Image Restoration for Multiple Degradation With Intrinsic Semantics Recovery
206. CVPR 2023Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring
207. ICLR 2023Bag of Tricks for Unsupervised Text-to-Speech
208. ICLR 2023BAYES RISK CTC: CONTROLLABLE CTC ALIGNMENT IN SEQUENCE-TO-SEQUENCE TASKS
209. ICLR 2023Causality Compensated Attention for Contextual Biased Visual Recognition
210. ICLR 2023Continuous pseudo-labeling from the start
211. ICLR 2023CUDA: Curriculum of Data Augmentation for Long-tailed Recognition
212. ICLR 2023D4AM: A General Denoising Framework for Downstream Acoustic Models
213. ICLR 2023Exploring Temporally Dynamic Data Augmentation for Video Recognition
214. ICLR 2023Graph Contrastive Learning for Skeleton-based Action Recognition
215. ICLR 2023In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations
216. ICLR 2023Jointly Learning Visual and Auditory Speech Representations from Raw Data
217. ICLR 2023On the complexity of nonsmooth automatic differentiation
218. ICLR 2023Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning
219. ICLR 2023Revisiting the Entropy Semiring for Neural Speech Recognition
220. ICLR 2023The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition
221. ICML 2023Facial Expression Recognition with Adaptive Frame Rate based on Multiple Testing Correction
222. ICML 2023Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization
223. ICML 2023Robust Speech Recognition via Large-Scale Weak Supervision
224. ICML 2023Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations
225. ICML 2023Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
226. ICML 2023Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition
227. NeurIPS 2023Incomplete Multimodality-Diffused Emotion Recognition
228. NeurIPS 2023Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer
229. NeurIPS 2023Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition
230. NeurIPS 2023Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition

FAQ

How many Speech Recognition papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

230 in total: 75 in 2023, 55 in 2024, 50 in 2025, 50 in 2026.

How many Speech Recognition papers are at NeurIPS 2026?

NeurIPS 2026 has 16 Speech Recognition papers, versus 22 the year before.

How many Speech Recognition papers are at ICLR 2026?

ICLR 2026 has 7 Speech Recognition papers, versus 7 the year before.

How many Speech Recognition papers are at ICML 2026?

ICML 2026 has 8 Speech Recognition papers, versus 5 the year before.

How many Speech Recognition papers are at CVPR 2026?

CVPR 2026 has 19 Speech Recognition papers, versus 16 the year before.

Which conference publishes the most Speech Recognition papers?

CVPR, with 114 papers from 2023 to 2026.