For more than three decades Roberto Pieraccini has been actively working towards the goal of building machines that can intelligently converse with humans using speech. The technologies that enable a machine to recognize the words of an utterance, understand its meaning, decide how to act on that, perform an action and generate a spoken message back to a user where very limited thirty years ago. In spite of those limitations, with the help of good design practices, effective tools, smart usage of data and machine learning, we relentlessly made strides in advancing the performance and bringing measurable value to users. The dream of a human-like automated agent has not been fully realized yet, and many problems remain to be solved, but we are at a time in history when those technologies can enable a machine like the Google Assistant to be light years ahead in performance and sophistication as compared with analogous efforts of the past.
This talk is about the story of that journey, the problems encountered and the solutions that helped shape today’s technology landscape in this area. It is the story of the relentless improvement of the spoken human-machine technology, until today’s successes and beyond. It is also about the excitement of being working, at this very moment in time, on an exciting project like the Google Assistant, and help create a possible future for the machines who talk.