CALL FOR PAPERS
Topics of interest for submission include, but are not limited to:
Topic 1: Intelligent Voice Technology
Speech Recognition and Synthesis (ASR/TTS)
Multilingual and low-resource speech processing
Emotional speech analysis and generation
Speech enhancement and denoising technology
Topic 3: Multimodal Information Processing
Voice-visual fusion technology
Multimodal sentiment computing
Cross-modal generation and retrieval
Medical multimodal generation
Topic 5: Natural Language Processing
Optimization of Large Language Model (LLM)
Machine translation
cross-language information processing
Text mining and knowledge graph construction
Dialogue systems and chatbots
Topic 2: Audio Signal Processing
Acoustic scene classification and event detection
Audio compression and coding technology
Music information retrieval and generation
Decoding of voice signals in brain-computer interfaces
Topic 4: Applications and Systems
The application of intelligent voice
Voice interaction hardware
Privacy protection and secure voice communication
Speech Forgery Detection and Defense
Topic 6: Artificial Intelligence and Deep Learning
Artificial & Computational Intelligence
End-to-end speech
Lightweighting and edge computing deployment
Adversarial attacks and model robustness
quantum computing in information processing