Latest Research in Speech Processing And Synthesis

Top Research Topics in Speech Processing And Synthesis

• Sound — 92 papers
• Audio and Speech Processing — 79 papers
• Computation and Language — 63 papers
• Speech Recognition and Synthesis — 14 papers
• Emotion and Mood Recognition — 8 papers
• Speech and Audio Processing — 7 papers
• Machine Learning — 5 papers
• Music and Audio Processing — 4 papers
• Computer Vision and Pattern Recognition — 4 papers
• Mobile and Web Applications — 3 papers

Highest-Cited Papers

1. Low resource multi-head self-attention based transformer for airborne acoustic classification system
2. MMedFD: A Real-world Healthcare Benchmark for Multi-turn Full-Duplex Automatic Speech Recognition
3. Phoneme- vs. Character-Level Targets and Selective State-Space Models for Intracortical Brain-to-Text
4. Qwen-Audio-3.0-Gen-Preview Technical Report
5. A Study on Online Mask-based Beamforming Using Per-channel Masking for Spatially Distributed Microphones
6. Audio-Anchored Fusion of Multi-Ratio DiT Reconstruction Residuals for Cross-Domain Audio Deepfake Detection
7. Prosody-driven Jailbreaks in Audio LLMs: A Controlled Study and Mechanistic Analysis
8. Unfolded Recursive Expectation-Maximization Neural Network For Speaker Tracking
9. A Multiplatform Pairing‑Protocol Client-Server Architecture and a concrete implementation example: An Android‑hosted Speech‑Recognition Pairing Server with a Multiplatform Client, providing Speech Recognition to different platform devices
10. Extracting Voice Styles from Frozen TTS Models via Gradient-Based Inverse Optimization
11. A Cross-lingual Comparison of Human and Classification Model Entrainment Behavior in Code-switched Speech Settings
12. Joint Text-Audio Alignment for EEG-to-Text Decoding in Chinese Speech Production and Perception
13. A Heliumspeech Unscrambling Method Based on Deep Learning with Phonetic Multi-Objective Optimization
14. A Multiplatform Pairing‑Protocol Client-Server Architecture and a concrete implementation example: An Android‑hosted Speech‑Recognition Pairing Server with a Multiplatform Client, providing Speech Recognition to different platform devices
15. A Multiplatform Pairing‑Protocol Client-Server Architecture and a concrete implementation example: An Android‑hosted Speech‑Recognition Pairing Server with a Multiplatform Client, providing Speech Recognition to different platform devices
16. Time-Frequency Consistency Learning for Robust Speech Deepfake Detection
17. VAD to the Bone: Ultra-Tiny Speech Activity Detection for Edge Deployment
18. From Semantics to Readout: Mechanistic Understanding of Audio Tokens after Fine-Tuning for Temporal Audio Grounding
19. Audio dequantization using instantaneous frequency
20. Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens

Sub-Regions

• Computation and Language — 94 papers
• Speech Recognition and Synthesis — 51 papers
• Sound — 49 papers
• Artificial Intelligence — 39 papers
• Audio and Speech Processing — 30 papers
• Speech and Audio Processing — 30 papers