Latest Research in Speech and Affective Computing

Top Research Topics in Speech and Affective Computing

• Sound — 169 papers
• Audio and Speech Processing — 91 papers
• Computation and Language — 71 papers
• Computer Vision and Pattern Recognition — 33 papers
• Emotion and Mood Recognition — 29 papers
• Speech Recognition and Synthesis — 18 papers
• Music and Audio Processing — 18 papers
• Artificial Intelligence — 13 papers
• Speech and Audio Processing — 10 papers
• Multimedia — 10 papers

Highest-Cited Papers

1. Long-Term Affective Persistence and Sentiment Transfer in Large Language Models
2. Intelligent music creation enhanced by graph neural networks and federated learning
3. Analysing Korean children's speech data for early childhood educational services: age-specific insights from text and audio analysis
4. Comprehensive review of traditional and deep learning approaches to text to speech synthesis
5. Tibetan-PASEM: Phonology-Aware Speech Evidence Matching for Low-Resource Tibetan Written-Query Keyword Spotting
6. Between accuracy and empathy: A comparative study of human and transformer-based multi-label emotion annotation
7. Audio-guided articulatory distillation for multilingual visual speech recognition with large language model decoding
8. Design and Efficacy of a Speaker Verification Method Combining CNN and Transformer for Secure Access Control
9. Expressive Dizi Synthesis: Unlimited Synthetic Datasets, Real–Synthetic Integration and Technique Labeling
10. Hybrid abstractive model using BioBERT and stacked LSTM for biomedical text summarization
11. Synaspot: A Lightweight, Streaming Multi-modal Framework for Keyword Spotting with Audio-Text Synergy
12. CookVoice: Unified Framework for Style Controllable Multi-Modal Human Voice Generation
13. Luna-TTS Family Technical Report
14. Deep Learning Based Relative Transfer Matrix Estimation for Multiple Sources and Multiple Microphones
15. Easper: An Accessible ASR Pipeline for Language Documentation
16. MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques
17. Surfacing the Unsaid: CUE-Bench for Affective Stance in Chinese Discourse
18. Hybrid Real- and Complex-Valued Neural Network Architecture for Speech Enhancement
19. Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning
20. Confucius4-TTS: Transcript-Free Cross-Lingual Zero-Shot TTS with a Learnable Speaker Encoder

Sub-Regions

• Neural Speech Synthesis — 249 papers
• Generative Music Modeling — 161 papers
• Multimodal Affective Reasoning — 84 papers
• Speech Emotion Dynamics — 33 papers