Mike McCourt of Invoca discusses how to automatically process and analysis voice data to classify it using machine learning. Felienne spoke with McCourt about the difficulties in processing audio of different qualities, in different languages and the applicability of different types of machine learning to voice data.
Show Notes
Related Links
- Kaldi
- Mozilla DeepSpeech
- Invoca engineering blog
- Invoca blog, (which is targeted more toward marketers than to engineers)
SE Radio theme: “Broken Reality” by Kevin MacLeod (incompetech.com — Licensed under Creative Commons: By Attribution 3.0)