Event Details

Registrations to date: 1

Every contact center leader has heard it: a caller repeating their name three times, getting more frustrated with each attempt. The dashboards look clean. Containment is up, confidence scores look fine. The system looks like it’s working, but your customer just had their worst interaction of the week, and none of your metrics caught it.

Analyzing voice-driven customer experience today means chasing answers across a dozen scattered signals, transcripts, sentiment scores, handle times, escalation rates, without a comprehensive map of the thing you’re actually measuring: a conversation. That map exists, and it’s called linguistics. With it, the scattered signals fall into their right spots and order, and you stop patching symptoms and start diagnosing the experience.

The map starts with a simple model. Every conversation runs on two channels: the form (sounds, words, timing, turns) and the meaning (the task, the situation, the feeling). Customers keep both channels aligned, with each other and with their partner’s, continuously and without thinking. A voice agent that serves them well has to do the same: keeping its form and meaning channels aligned, with each other, and with the customer’s, constantly and seamlessly.

The map survives every technology shift, because it describes the conversation, not the implementation. From it, you get both halves of the job: design questions for building better customer experiences, and a matrix that turns “the customer was frustrated” or “the bot just didn’t get it” into concrete, measurable, fixable failure modes, the missing rows in your voice-of-customer analysis.

Who this is for: CX and customer service leaders, analysts working with call and chat data, voice AI practitioners, and anyone who’s watched clean dashboards while their customers quietly suffered.

About Our Speaker(s)

Midam Kim is an ML Engineer at ServiceNow, where she builds and evaluates a multilingual voice AI platform spanning a dozen languages. She holds a PhD in Linguistics from Northwestern University and has backgrounds in linguistics, speech science, cognitive science, machine learning, and business. Her work sits at the rare intersection of production ML engineering and speech science—translating decades of linguistic research into the engineering decisions voice AI teams are making right now.