Latest Research in Speech and Multimodal Analytics

Top Research Topics in Speech and Multimodal Analytics

• Sound — 154 papers
• Intelligence, Security, War Strategy — 132 papers
• Audio and Speech Processing — 126 papers
• Computer Vision and Pattern Recognition — 120 papers
• Computation and Language — 104 papers
• Emotion and Mood Recognition — 33 papers
• Speech Recognition and Synthesis — 26 papers
• Artificial Intelligence — 24 papers
• Machine Learning — 16 papers
• Music and Audio Processing — 13 papers

Highest-Cited Papers

1. DOTA-ME-CS: daily oriented text audio-Mandarin English-Code switching dataset (1 citations)
2. A dual-domain guided emotion-specialized swin transformer for enhancing speech emotion recognition
3. EuroMillions Breakthrough Mining — 4317 Sources, 38847 Leads Extracted — E8 Intelligence Research
4. Music Genre Classification Algorithm Based on Multi-Scale Fusion
5. Towards inclusive voice biometrics: Dysarthria-discriminative embeddings for ASV system
6. EuroMillions Breakthrough Mining — 4348 Sources, 39103 Leads Extracted — E8 Intelligence Research
7. EuroMillions Breakthrough Mining — 4348 Sources, 39103 Leads Extracted — E8 Intelligence Research
8. EuroMillions Breakthrough Mining — 4317 Sources, 38847 Leads Extracted — E8 Intelligence Research
9. Event-Grounded Football News Generation from Match Videos with Parameter-Efficient Large Language Models
10. Speech intelligibility comparison of standalone and two-stage deep learning architectures for behind-the-ear-to-binaural enhancement
11. EuroMillions Breakthrough Mining — 4271 Sources, 38419 Leads Extracted — E8 Intelligence Research
12. EuroMillions Breakthrough Mining — 4268 Sources, 38386 Leads Extracted — E8 Intelligence Research
13. Reading User Distress From the Inside: Do a Language Model's Hidden States Track a Person's Distress Better Than the Model's Own Reply Does?
14. A2SSC: An Agent-based Adaptive Semantic Speech Communication System
15. Adaptive learning behavior recognition using multimodal transformer based dynamic modality regulation
16. EuroMillions Breakthrough Mining — 4288 Sources, 38586 Leads Extracted — E8 Intelligence Research
17. EuroMillions Breakthrough Mining — 4269 Sources, 38397 Leads Extracted — E8 Intelligence Research
18. Dual-stream audio–visual Transformer fusion for harmful video content detection
19. DESED and DataSED precomputed caches for Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification
20. EuroMillions Breakthrough Mining — 4271 Sources, 38419 Leads Extracted — E8 Intelligence Research

Sub-Regions

• Conversational Speech Processing — 360 papers
• Strategic Intelligence Mining — 134 papers
• Multimodal Video Perception — 118 papers
• Computational Music Audio — 108 papers
• Affective Multimodal Recognition — 96 papers