Please log in to watch this conference skillscast.
“Solving speech recognition” is one of the achievements which brought deep learning to front stage in the last few years. However the mechanics of how deep learning is applied in a speech engine are described less often in divulgative articles than, say, those of CNN image classification. In this lightning talk, Sebastien will fill this gap.
YOU MAY ALSO LIKE:
- Points of contact between big data engineering and machine learning - Intermediate (SkillsCast recorded in July 2017)
- Automating Elaborate-Transform-Load for Busy Data Scientists (SkillsCast recorded in October 2019)
- Apache Druid: the fast, real-time, open-source analytics data store (SkillsCast recorded in September 2019)
Solving speech recognition - Intermediate
Sébastien Bratières has spent 15 years in the speech and language industry in different European ventures, starting from the EU branch of Tellme Networks (now Microsoft) to startups in speech recognition and virtual conversational agents. These days, Sébastien is finishing a PhD in statistical machine learning with Zoubin Ghahramani at the University of Cambridge, UK, and will soon be looking for his next challenges. Sébastien lives in Rome, Italy, with his wife and two children.