Thesis – Voice Interaction for Intercom Devices
Core
Researching voice interaction features for intercom devices, including lip-syncing, audio transcription, speech synthesis, and language identification.
Role type
Master/Bachelor thesis student in speech and language technology
Builds
Research prototypes and lightweight ML models for voice-first intercom systems
Domain
Consumer electronics / Speech and Language Technology
Deliverable
research
Required skills
Machine learning, speech-to-text, speech synthesis, natural language processing, audio analysis
Preferred skills
Prosody modeling, real-time processing, language identification
Technologies
Python, TensorFlow, PyTorch, Kaldi, Whisper, OpenAI Whisper
Responsibilities
Develop lightweight ML models for prosody prediction, build real-time speech analysis pipelines, implement call transcription or language detection systems
Seniority
Student (Master or Bachelor)
