Listen "040: The multilayered anatomy of a generative AI voice assistant"
Episode Synopsis
Send us a textIt's getting technical up in here! Kylie welcomes PolyAI CTO & Co-Founder Shawn Wen to the show to discuss the complexities of building high-quality voice AI systems. From the limitations of large language models (LLMs) to the nuances across each layer of the tech stack, they'll cover setting up audio channels, streaming speech recognition, voice activity detection, and the uniquely global challenge of handling different accents and languages. Shawn gives away a bit of our secret sauce, while underscoring the importance of adapting technology to user characteristics and enterprise demands. 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
ZARZA We are Zarza, the prestigious firm behind major projects in information technology.