Computers learn to convert human speech to text with speech recognition models. Google Machine Learning Engineer Roza Chojnacka shares her expertise in Speech Recognition algorithms by discussing what it is, how it works, and the differences between traditional speech recognition systems and the more common ML model.
Speech-to-Text →
Speech Processing →
Introducing CVSS: A Massively Multilingual Speech-to-Speech Translation Corpus →
Learn more →
Watch more Women Techmakers in 60 seconds! →
Subscribe for more Women Techmakers videos →
source
