Optimizing Voice Commands and IVRs to Speech Analytics (Cloud Next '19)

Опубликовано 11 апреля 2019, 19:36

With cloud-based services, speech recognition is easy to get started with, and it is more accurate and closer to human levels than it’s ever been before. But user expectations and increasingly complex natural-language based use cases have also raised the bar, and what was “good enough” before is not sufficient anymore for creating a great end-user experience.

In this session we will show you how to get the most out of Cloud Speech-to-Text and tune it so you could build the best experience for your users.

Another big challenge businesses face is making sense out of large amounts of speech. Many businesses haven’t been taking full advantage of the data that’s locked in their call center recordings. We will demonstrate how with our partners we can help you build your own speech analytics dashboards that solve business problems by extracting diarized transcripts, sentiment, silence logs and other signals - all without requiring any technical experience.


Beyond Just Speech-To-Text → bit.ly/2TS6twZ

Watch more:
Next '19 ML & AI Sessions here → bit.ly/Next19MLandAI
Next ‘19 All Sessions playlist → bit.ly/Next19AllSessions

Subscribe to the GCP Channel → bit.ly/GCloudPlatform


Speaker(s): Dan Aharon, Kevin Northover

Session ID: MLAI208
product: Cloud - General; fullname: Dan Aharon; event: Google Cloud Next 2019;