Applications · speech and audio papers, 2023–2026

Application area: speech_and_audio

Scope: NeurIPS, ICLR, ICML and CVPR, 2023–2026. 1,722 papers are tagged with this topic.

Key findings

Papers per year

Papers per venue

Counts by year and venue

Applications · speech and audio papers by year and venue
YearNeurIPSICLRICMLCVPRTotal
202331273227117
2024531285244277
2025982927243505
202615345117148823

Representative papers

Spread across years and venues so every edition shows up

All Applications · speech and audio papers

YearAll2023202420252026
VenueAllNeurIPSICLRICMLCVPR

327 papers, page 5 of 7

  1. ICML 2025Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction
  2. ICML 2025Geometric and Physical Constraints Synergistically Enhance Neural PDE Surrogates
  3. ICML 2025Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs
  4. ICML 2025High-Fidelity Simultaneous Speech-To-Speech Translation
  5. ICML 2025Implicit Riemannian Optimism with Applications to Min-Max Problems
  6. ICML 2025KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
  7. ICML 2025LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs – No Silver Bullet for LC or RAG Routing
  8. ICML 2025Learn Singularly Perturbed Solutions via Homotopy Dynamics
  9. ICML 2025Learning from others' mistakes: Finetuning machine translation models with span-level error annotations
  10. ICML 2025Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive Supervision
  11. ICML 2025Learning with Expected Signatures: Theory and Applications
  12. ICML 2025Long-Form Speech Generation with Spoken Language Models
  13. ICML 2025Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic
  14. ICML 2025MATS: An Audio Language Model under Text-only Supervision
  15. ICML 2025MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-text Decoding
  16. ICML 2025MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition
  17. ICML 2025Multi-band Frequency Reconstruction for Neural Psychoacoustic Coding
  18. ICML 2025MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners
  19. ICML 2025NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
  20. ICML 2025OmniAudio: Generating Spatial Audio from 360-Degree Video
  21. ICML 2025One Wave To Explain Them All: A Unifying Perspective On Feature Attribution
  22. ICML 2025Otter: Generating Tests from Issues to Validate SWE Patches
  23. ICML 2025Overcoming Non-monotonicity in Transducer-based Streaming Generation
  24. ICML 2025OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models
  25. ICML 2025PDE-Transformer: Efficient and Versatile Transformers for Physics Simulations
  26. ICML 2025Playmate: Flexible Control of Portrait Animation via 3D-Implicit Space Guided Diffusion
  27. ICML 2025Policy Filtration for RLHF to Mitigate Noise in Reward Models
  28. ICML 2025Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications
  29. ICML 2025QuanONet: Quantum Neural Operator with Application to Differential Equation
  30. ICML 2025Reducing Tool Hallucination via Reliability Alignment
  31. ICML 2025RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior
  32. ICML 2025Rethink GraphODE Generalization within Coupled Dynamical System
  33. ICML 2025ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networks
  34. ICML 2025SING: Spatial Context in Large Language Model for Next-Gen Wearables
  35. ICML 2025Sortformer: A Novel Approach for Permutation-Resolved Speaker Supervision in Speech-to-Text Systems
  36. ICML 2025Steering Protein Language Models
  37. ICML 2025Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version Matching
  38. ICML 2025The Brain's Bitter Lesson: Scaling Speech Decoding With Self-Supervised Learning
  39. ICML 2025The dark side of the forces: assessing non-conservative force models for atomistic machine learning
  40. ICML 2025TraceGrad: a Framework Learning Expressive SO(3)-equivariant Non-linear Representations for Electronic-Structure Hamiltonian Prediction
  41. ICML 2025UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition Confirmation
  42. ICML 2025Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning
  43. ICML 2025XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
  44. ICML 2024$\bf{\Phi}_\textrm{Flow}$: Differentiable Simulations for PyTorch, TensorFlow and Jax
  45. ICML 2024An Intrinsic Vector Heat Network
  46. ICML 2024AND: Audio Network Dissection for Interpreting Deep Acoustic Models
  47. ICML 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities
  48. ICML 2024Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
  49. ICML 2024Biharmonic Distance of Graphs and its Higher-Order Variants: Theoretical Properties with Applications to Centrality and Clustering
  50. ICML 2024Box Facets and Cut Facets of Lifted Multicut Polytopes

Ask about this trend from Claude or Cursor

Connect the Paperlist MCP and your assistant can pull the numbers on this page while you draft a survey, pick a direction or plan a submission: papers per year and venue, growth, the fastest-rising sub-themes and representative papers, shaped around your question.

Copy this prompt into your assistant

Use paperlist to show how Applications · speech and audio papers grew at ICLR from 2023 to 2026, and which year jumped the most.

Tool the assistant calls: get_topic_stats {"topic": "app-speech-and-audio"}

Set up Paperlist MCP in two minutes (Claude Code, Cursor, Codex, ChatGPT)

FAQ

How many Applications · speech and audio papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?
1,722 in total: 117 in 2023, 277 in 2024, 505 in 2025, 823 in 2026.
How many Applications · speech and audio papers are at NeurIPS 2026?
NeurIPS 2026 has 153 Applications · speech and audio papers, versus 98 the year before.
How many Applications · speech and audio papers are at ICLR 2026?
ICLR 2026 has 451 Applications · speech and audio papers, versus 292 the year before.
How many Applications · speech and audio papers are at ICML 2026?
ICML 2026 has 171 Applications · speech and audio papers, versus 72 the year before.
How many Applications · speech and audio papers are at CVPR 2026?
CVPR 2026 has 48 Applications · speech and audio papers, versus 43 the year before.
Which conference publishes the most Applications · speech and audio papers?
ICLR, with 898 papers from 2023 to 2026.

More in Application Domains