Google previewed a new skill for its Google Assistant during Google I/O this week. Called Google Duplex
Main purpose is to make calls on our behalf, conducting the conversations in a natural sounding and flowing manner to help perform “real world” tasks.A test is conducted which is used to determine if an Artificial Intelligence’s behavior is indistinguishable from that of a human – high praise indeed.
Step change in Google Duplex:
These features made us to think talking with a human.Google Duplex employs the TensorFlow Extended (TFX) Machine Learning platform to create a Recurrent Neural Network (RNN) with speech processing duties being handled via an Automatic Speech Recognition (ASR) and Text To Speech (TTS) engines controlling intonation depending on the circumstances.
ASR converts recepient speech into text, text is analysed within context,within response converted into speech to customer via TTS.
Google has employed speech disfluencies to create breaks during the conversation, for example, “erms”, “hmms” that makes the speech produced by Google Duplex even more naturally sounding.
Google Duplex is self-monitoring, in the event of a task that it can’t complete autonomously it signals a human operator who will complete the task.