Text-to-Speech papers, 2023–2026

Key findings

• Text-to-Speech went from 125 papers in 2023 to 200 in 2026, roughly 1.6x in three years.
• NeurIPS publishes the most Text-to-Speech work: 204 papers from 2023 to 2026, 33% of the four-venue total.
• The fastest-growing overlap is with Object Detection: papers tagged with both rose from 1 in 2023 to 10 in 2026.
• Among the 5 topics under Audio and Speech, it ranks #2 by 2026 paper count; the fastest grower in the group, Audio Generation, is up 4.3x versus 1.6x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026CAPER: Clause-Aligned Process Supervision for Text-to-SQL
• ICML 2026Black-Box Detection of LLM-Generated Text Using Generalized Jensen Shannon Divergence
• ICLR 2026CSRv2: Unlocking Ultra-Sparse Embeddings
• CVPR 2026Aligning Text Images and 3D Structure Token-by-Token
• NeurIPS 2025AdaDetectGPT: Adaptive Detection of LLM-Generated Text with Statistical Guarantees
• ICML 2025How to Synthesize Text Data without Model Collapse?
• ICLR 2025AI as Humanity’s Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
• CVPR 2025AMO Sampler: Enhancing Text Rendering with Overshooting
• NeurIPS 2024SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark
• ICML 2024Adaptive Text Watermark for Large Language Models
• ICLR 2024Are Models Biased on Text without Gender-related Language?
• CVPR 2024Kernel Adaptive Convolution for Scene Text Detection via Distance Map Prediction
• NeurIPS 2023[Re] Pure Noise to the Rescue of Insufficient Data
• ICML 2023Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
• ICLR 2023Bag of Tricks for Unsupervised Text-to-Speech
• CVPR 20233D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions
• NeurIPS 2026DiffScore: Text Evaluation Beyond Autoregressive Likelihood
• ICML 2026CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
• ICLR 2026DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations
• CVPR 2026Learning complete and explainable visual representations from itemized text supervision

All Text-to-Speech papers

621 papers, page 3 of 13

101. ICML 2026Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL
102. ICML 2026Black-Box Detection of LLM-Generated Text Using Generalized Jensen Shannon Divergence
103. ICML 2026Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
104. ICML 2026CoCoEmo: Composable and Controllable Human-Like Emotional TTS via Activation Steering
105. ICML 2026DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs
106. ICML 2026Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability
107. ICML 2026Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration
108. ICML 2026Fast Byte Latent Transformer
109. ICML 2026From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space
110. ICML 2026Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
111. ICML 2026GraphFLEx: Unsupervised Structure Learning $\underline{\text{F}}$ramework for $\underline{\text{L}}$arge $\underline{\text{Ex}}$panding $\underline{\text{Graph}}$s
112. ICML 2026Guided Star-Shaped Masked Diffusion
113. ICML 2026Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
114. ICML 2026MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
115. ICML 2026Minimizing Mismatch Risk: A Prototype-Based Routing Framework for Zero-shot LLM-generated Text Detection
116. ICML 2026MoST: Mixing Speech and Text with Modality-Aware Mixture of Experts
117. ICML 2026Noisy-Channel Minimum Bayes Risk Decoding
118. ICML 2026On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective
119. ICML 2026Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech
120. ICML 2026Optimizing Diversity and Quality through Base-Aligned Model Collaboration
121. ICML 2026PACEAttention: Principled and Adaptive Feature Compression-Expansion Grounded in the Geometry of $\text{MCR}^2$
122. ICML 2026PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
123. ICML 2026Quaternion Self-Attention with Shared Scores
124. ICML 2026Query-Based Asymmetric Modeling with Decoupled Input–Output Rates for Speech Restoration
125. ICML 2026SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
126. ICML 2026Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment
127. ICML 2026Separating Representation from Reconstruction Enables Scalable Text Encoders
128. ICML 2026SoftMatcha 2: A Fast and Soft Pattern Matcher for Trillion-Scale Corpora
129. ICML 2026Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech
130. ICML 2026Text Has Curvature
131. ICML 2026Text-Conditional JEPA for Learning Semantically Rich Visual Representations
132. ICML 2026TextME: Bridging Unseen Modalities Through Text Descriptions
133. ICML 2026Unlocking Speech–Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning
134. NeurIPS 2026A Unified Audio Language Model with Text-Aligned Factorized Audio Tokenization
135. NeurIPS 2026Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning
136. NeurIPS 2026Artificial Aphasias in Lesioned Language Models
137. NeurIPS 2026Beyond Sparse Captions: Aligning Slide-Level Text and Patch-Level Vision in Pathology
138. NeurIPS 2026Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection
139. NeurIPS 2026BrainWhisperer: Leveraging Whisper for Speech Decoding in Neuroprosthetics
140. NeurIPS 2026Can Bits Seal Language?
141. NeurIPS 2026CAPER: Clause-Aligned Process Supervision for Text-to-SQL
142. NeurIPS 2026CRESiST: Self-Enhancing Exploritive Policy Learning for Simultaneous Speech Translation
143. NeurIPS 2026DiffScore: Text Evaluation Beyond Autoregressive Likelihood
144. NeurIPS 2026Do Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling
145. NeurIPS 2026DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech
146. NeurIPS 2026Efficient Brain-to-Speech Decoding with Fixed-Delay Spiking Neural Networks
147. NeurIPS 2026Full-Duplex Speech-Motion Model for Dyadic Interaction
148. NeurIPS 2026Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap
149. NeurIPS 2026HalluciText: Mitigating Text Hallucinations in Diffusion-Based Image Restoration
150. NeurIPS 2026Handwritten Text Recognition Lives in the High-Pixel Variance Subspace

FAQ

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

621 in total: 125 in 2023, 145 in 2024, 151 in 2025, 200 in 2026.

How many Text-to-Speech papers are at NeurIPS 2026?

NeurIPS 2026 has 67 Text-to-Speech papers, versus 45 the year before.

How many Text-to-Speech papers are at ICLR 2026?

ICLR 2026 has 43 Text-to-Speech papers, versus 32 the year before.

How many Text-to-Speech papers are at ICML 2026?

ICML 2026 has 36 Text-to-Speech papers, versus 16 the year before.

How many Text-to-Speech papers are at CVPR 2026?

CVPR 2026 has 54 Text-to-Speech papers, versus 58 the year before.

Which conference publishes the most Text-to-Speech papers?

NeurIPS, with 204 papers from 2023 to 2026.