Latest Research in Neural Speech Synthesis

Top Research Topics in Neural Speech Synthesis

• Sound — 72 papers
• Audio and Speech Processing — 69 papers
• Computation and Language — 45 papers
• Speech Recognition and Synthesis — 17 papers
• Speech and Audio Processing — 9 papers
• Machine Learning — 6 papers
• Artificial Intelligence — 5 papers
• Music Technology and Sound Studies — 4 papers
• Computer Vision and Pattern Recognition — 4 papers
• Mobile and Web Applications — 3 papers

Highest-Cited Papers

1. Intelligent music creation enhanced by graph neural networks and federated learning
2. Analysing Korean children's speech data for early childhood educational services: age-specific insights from text and audio analysis
3. Comprehensive review of traditional and deep learning approaches to text to speech synthesis
4. Tibetan-PASEM: Phonology-Aware Speech Evidence Matching for Low-Resource Tibetan Written-Query Keyword Spotting
5. Audio-guided articulatory distillation for multilingual visual speech recognition with large language model decoding
6. Design and Efficacy of a Speaker Verification Method Combining CNN and Transformer for Secure Access Control
7. Synaspot: A Lightweight, Streaming Multi-modal Framework for Keyword Spotting with Audio-Text Synergy
8. CookVoice: Unified Framework for Style Controllable Multi-Modal Human Voice Generation
9. Luna-TTS Family Technical Report
10. Deep Learning Based Relative Transfer Matrix Estimation for Multiple Sources and Multiple Microphones
11. Easper: An Accessible ASR Pipeline for Language Documentation
12. Hybrid Real- and Complex-Valued Neural Network Architecture for Speech Enhancement
13. Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning
14. Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder
15. Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization
16. The SLT 2026 SmartGlasses Challenge: Benchmarking Egocentric Multi-Talker Speech Recognition and Understanding with Audio-Language Models
17. MiDashengLM-Gen: Unified Audio Scene Generation via LLM-Driven Autoregressive Flow Matching
18. On-Policy Self-Distillation for Multi-Dialect ASR: Mastering Dialects, Retaining Mandarin
19. Rethinking Language Model-Based Generative Speech Enhancement in the Latent Space of a Neural Audio Codec
20. RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation

Sub-Regions

• Computation and Language — 115 papers
• Machine Learning — 42 papers
• Audio and Speech Processing — 33 papers
• Speech and Audio Processing — 30 papers
• Sound — 25 papers
• Audio and Speech Processing — 1 papers