Sound, Search and Semantics

It’s not breaking news that voice search is the emerging technology of greatest interest, but what hasn’t been demystified is how it works. This session will uncover how the algorithm functions at a structural level by dissecting Google’s Automatic Speech Recognition and deciphering the nuances of the spoken word as they apply to semantic search.

After this session, you’ll be able to:

  • Understand the two fundamental parts of Google’s Automatic Speech Recognition (ASR): how sound is processed and how speech modeling is conducted
  • Know exactly what the four metrics Google uses to track the quality of the system are
  • Apply given tactics on how to target content by searcher need states to your own strategy