Freelance AI Speech Recognition Engineer Role - BrusselsA client are building cutting-edge voice technology track and monitor customer voice to develop insights to use in future use cases. From real-time transcription to multilingual voice assistants, my client design intelligent systems that inform future practices.
Design, build, and optimise end-to-end speech-to-text (STT) and natural language understanding (NLU) pipelines.
Fine-tune and evaluate ASR models (e.g. Wav2Vec 2.0, Whisper, Kaldi, or DeepSpeech).
Implement speaker diarization, noise reduction, and language modeling techniques.
Collaborate with product teams to integrate real-time transcription and voice services into production systems.
Drive innovation in voice AI with research and experimentation in neural acoustic modeling, beam search decoding, or self-supervised learning
Must have experience with Speech Recognition and/or Speech-to-Text data
The role is Brussels based
Project is planned to last 3 years
Hybrid working
Large client with real world impact
g2 Recruitment are committed to equality of opportunity for all applications from individuals are encouraged regardless of age, disability, sex, gender reassignment, sexual orientation, pregnancy and maternity, race, religion or belief and marriage and civil partnerships or any other characteristic protected by law.
