ZARZA We are Zarza, the prestigious firm behind major projects in information technology.
Listen "044: Speech Recognition and Spoken Language Understanding (SLU)"
Episode Synopsis
Send us a textIn our second technical dive in the the anatomy of a voice assistant, Kylie hosts Shawn Wen, co-founder and CTO of Poly AI, to analyze the complexities of building voice assistants. He highlights the challenges faced in speech recognition, such as dealing with errors, latency, and user experience. Shawn also discusses the inefficiencies of converting chatbots to voice assistants and the nuances that must be managed, including managing speech recognition models, right-sizing latency, agile dialogue design, and dealing with telephony filters. He emphasizes that optimizing these systems isn't just a technical problem but a multifaceted user experience challenge. Follow PolyAI on LinkedIn Watch this and other episodes of the Deep Learning pod on YouTube
More episodes of the podcast Deep Learning with PolyAI
Can journalism teach us how to trust AI?
04/12/2025
What does truly multilingual CX sound like?
13/11/2025
Can we solve AI's "deer-in-headlights" problem? (with Dan Miller, founder of Opus Research)
16/10/2025
Should hyper-growth brands still pick up the phone? (with Austin Towns, CTO of Hello Sugar)
16/10/2025
Your new favorite colleagues aren’t human
04/09/2025
In God we trust