ICSMACS'26

Tracks and Topics

Submissions are welcome (but not limited) to the following topics :

Track 1
Speech and Signal Processing
  • Speech recognition, synthesis, enhancement, and separation
  • Speech Coding
  • Spoken Language Identification
  • Speaker identification, verification, diarization
  • Emotion Detection, paralinguistics, and affective speech analysis
  • End-to-end and self-supervised models for speech/audio representation
  • Robust, multilingual, and low-resource speech systems
  • Speech command recognition and spoken language understanding
  • Audio event detection and sound scene analysis
  • Deepfake speech detection and spoofing countermeasures
  • Benchmarking resources, speech datasets, and evaluation methodologies
  • Biomedical signal processing for health tech
  • Image and video processing
  • Pattern recognition
Track 2
Multimodal Human-Computer Interaction and Intelligent Interfaces
  • Multimodal interaction: speech, gesture, gaze, haptics, vision
  • Audio-visual signal processing for human-computer interaction
  • Large Multimodal Models (LMMs) and generative AI
  • Embodied conversational agents, avatars, and virtual assistants
  • Context-aware, adaptive, and explainable multimodal systems
  • Fusion and alignment of multimodal signals (vision, audio, text, bio-signals)
  • Multimodal behavior analysis : emotion, intent, engagement
  • Computer vision for perception, tracking, and activity recognition
  • Immersive, accessible, and inclusive multimodal applications
  • Human-robot interaction and AI-driven assistive systems
  • Interaction in VR, AR, and and mixed reality environments
Track 3
Natural Language Processing & Generative AI
  • Large Language Models (LLMs) for generation, understanding, and dialogue
  • Prompt engineering, fine-tuning, and domain adaptation
  • Multilingual, low-resource, and cross-lingual NLP
  • Dialogue systems and conversational AI
  • Information extraction, summarization, and knowledge representation
  • Sentiment, emotion, and opinion analysis in text
  • Fact-checking, misinformation detection, and ethical AI for NLP applications
  • Text command ,  intent recognition and spoken language understanding
  • Text Categorization ,  Classification and topic modeling
  • Natural Language Understanding (NLU) and semantic parsing
  • NLP for multimodal, social-impact, and assistive applications
Track 4
Advanced Communication Systems and Intelligent Networking
  • Next-generation networks (5G/6G and beyond) 
  •  IoT, vehicular networks (VANET), and specialized communications
  • AI & ML for network optimization , spectrum management and orchestration
  • Edge AI, federated learning, and distributed intelligence
  • Multimedia signal processing and smart city applications
  • Quantum, optical, and cognitive communication systems
  • Software-defined networks and radio systems
  • Sustainable and energy-efficient network infrastructures
  • Security, privacy, cybersecurity, and digital forensics
  • Compressed sensing, time-series analysis and anomaly detection
  • Advanced source and speech coding for modern communication networks
  • Channel Coding and Error Correction
Track 5
Hardware and System Implementation for Intelligent Communication
  • Edge AI and On-device Processing for speech and multimodal applications
  • Neuromorphic Computing for Speech , audio, and multimodal signal processing
  • FPGA and ASIC Design for AI Acceleration
  • Low-Power and Energy-Efficient Hardware architectures
  • Real-time and Embedded Multimodal Systems
  • Hardware-Aware AI algorithm design and optimization
  • System-on-Chip (SoC) Design for Intelligent Communication systems
  • Prototyping , testing, and development platforms
  • Benchmarking and Performance Evaluation of Hardware Platforms
  • Hardware Security and trusted execution for embedded AI
  • AI-powered assistive and rehabilitation technologies for speech and hearing disorders