Description

In this role, you will:

  • Design, evaluate and select the ASR/TTS/Audio ML models and underlying software architecture to be used in the next-generation automotive infotainment middleware
  • Elevate the in-car experience across different car-lines worldwide by crafting the best-of-class AI-powered infotainment functionality
  • Select and tune of the best ASR/TTS/Audio ML models and incorporate them in the wider automotive infotainment middleware software architecture 
  • Design training protocols as well as continuous improvement of the software stack reflecting advancements in the field of ML

What you will need to succeed:

  • Experience in the areas of Machine Learning, Deep Learning, Speech Recognition, Speech Synthesis and Audio Data Processing
  • Experience with state-of-the-art speech recognition models and developing ASR-systems (e.g. using Kaldi, Wav2Vec, Whisper, DeepSpeech)
  • Fundamental knowledge in developing and evaluating TTS systems (e.g. using XTTS, WaveNet, Tacotron)
  • Experience with performance evaluation and optimization of Audio/Speech Processing algorithms
  • Strong knowledge of Python, C/C++, PyTorch, TensoFlow, Keras
  • Good written and verbal English communication skills

Key Skills
Education

Any Graduate

Back To Jobs