Best Practices for Active Listening in ASR (Video)
Learn more about customer self-service at the next SpeechTEK conference.
Read the complete transcript of this clip:
Frank Schneider: In active listening it's important to be ready to serve, but not impose solutions. So we're working on actions that say we know the top needs based on intent, based on this listening but relative the meaningful time, place, and audience factors.
We want to uncover outcomes for those needs or intents. We're connecting that intent understanding to as many customer journey analytics that are in place as possible.
Can I get to know when someone asks this intent to the IVR? Then they escalate, where else have they gone? How much can I bring in from CRM?
Because we want to uncover outcomes for those needs or intents, we feel that through active listening or using AI appropriately, you're going to map improvements before you even offer a solution.
In the technology that we've been working on and consulting we've been doing, we've been trying to say, “Let's listen to your customers for a month. Let's never interrupt the customer experience. Let's show all the possibilities in real time of the things we could have been doing. Let's practice tuning for those situations, but never actually jump in until we say, maybe, ‘You're feeling that the confidence score, let's just give it a number on a scale of one to ten is a four when we first start playing with it. The first time you decide to mess with a customer overall, it's at a seven.’ We're going to say, ‘Here are the 12 places we found a nine, let's go there first. Let's try there.’ So that you're not learning on the backs of customers.”
Everything that we're developing, that we're recommending, is not just our own technology.
It's about being centralized and agile without being intrusive.
So, often times when you go to sort of bigger AI stacks, you're going to have to not just be intrusive on the customer experience perspective. You're going to have to take everything that comes with it.
There's no way to pick and choose which layers of value you want. Take the whole sweep.
So, we're trying to not learn on your customer's backs. We won’t force you to have all of one particular stack or solution.
Because of that, we're not going to limit sources of context and memory. If we can leverage other AIs and other bots, we can do that.
Omilia's Quinn Agen discusses the value of context and memory in delivering human-like interactions in self-service contact centers in this clip from SpeechTEK 2018.
Artificial Solutions CEO Andy Peart plots out a roadmap for mainstream enterprise-level adoption of conversational AI in this clip from SpeechTEK 2018.
SpeakEasy AI CEO Frank Schneider explains how AI and active listening improve ASR accuracy in this clip from SpeechTEK 2018.
Ulster University Professor Michael McTear discusses how contemporary natural language-based intelligent agents use intents and entities rather than traditional parse trees in this clip from SpeechTEK 2018.
Ulster University Professor Michael McTear identifies key resources for chatbot design best practices as well as tools and frameworks for building voice-user interfaces in this clip from SpeechTEK 2018.
Ulster University Professor Michael McTear discusses how interactions differ with different intelligent agents, from one-shot dialogue to system-directed dialogue and mixed-initiative in this clip from his presentation at SpeechTech 2018.
Ulster University Professor Michael McTear breaks down the intelligent agent field in terms of type, technology, and functionality in this clip from SpeechTEK 2018.
Omilia's Quinn Agen discusses the way an an end-to-end conversational approach in machine-to-human interaction helps deliver satisfying contact center experiences in this clip from SpeechTEK 2018.
Omilia's Quinn Agen discusses the advantages of taking a conversational approach in automated contact center customer care in this clip from SpeechTEK 2018.
Aspect's Andreas Volmer discusses the value of visually representing conversational flow logic in chatbot design, and explores the advantages of a language-based approach over a statistically based approach in this clip from SpeechTEK 2018.
Aspect's Andreas Volmer discusses key components of a rules-based approach to chatbot design based on a robust language model in Part 1 of this two-part series from SpeechTEK 2018.