All posts by SpeechTEK

STKU-1: Natural Language Understanding

SpeechTEK University – Sunday 23 April 
13:30 – 16:30

Natural language interaction with automated agents in call centers, with chatbots, and virtual assistants on mobile devices is becoming more and more common. Through developer tools such as Microsoft LUIS, IBM Watson, the Alexa Skills Kit, and Nuance Mix, natural language understanding capabilities are becoming increasingly accessible to developers who want to provide natural interfaces to their applications. In addition, new developments in machine learning such as Deep Learning are leading to rapid improvements in the technology. This workshop covers three topics in natural language interaction. First, we review the spectrum of different types of natural language applications. Then, we look at the technologies that underlie natural language interaction. Finally, we review the natural language understanding development process and work hands-on with some of the current development tools. Attendees are welcome to bring their own ideas for applications for discussion. Bring your laptops.

Presented by: Deborah Dahl

STKU-2: The Nuts & Bolts of Tuning a Speech Application

SpeechTEK University – Sunday 23 April 
13:30 – 16:30

The workshop provides step-by step guidelines of the speech application tuning process, starting with data collection, data transcriptions, and data tagging and going all the way to delivering a customer-focused recommendation report. Participants gain firsthand understanding of the three aspects of tuning: speech recognition performance, grammar, and dialogue design. The course examines whole call recording tools as well as tools that capture speech event logs and produces metrics. Participants engage in a structured tuning data analysis that targets high-usage dialogue states. In addition to traditional methods, the course introduces an innovative approach to tuning by combining a heuristic usability evaluation with the analysis. This simple, low-cost, low-impact usability assessment provides a caller focus and translates directly to building a business case for the tuning recommendations. Finally, the course explores how tuning methods need to adapt to the broader speech landscape that now includes multi-channel applications, in-car applications, wearables, and mobile devices.

Presented by: Nancy Gardner

STKU-3: Natural Language Understanding for Chatbots: Issues & Solutions

SpeechTEK University – Sunday 23 April 
13:30 – 16:30

In order to provide a flexible and intelligent service to users, chatbots must be able to understand natural language text and to engage in conversational interaction. The first part of this tutorial introduces a range of natural language understanding (NLU) technologies and highlights those that are particularly relevant for chatbot developers. The second part of the tutorial provides a hands-on exploration of the tools. was acquired by Google in 2016 and is being used to provide NLU and conversational capabilities for Google Assistant. Learn how to use to parse messages into structured data, to predict the next actions to be performed by your bot, and to create slot-filling dialogues. Bring your laptops to develop a sample chatbot.

Presented by: Michael McTear

Speeding to Success: Quantifying the Customer Experience

Welcome & Opening Keynote – Monday 24 April 
08:45 – 09:45

How do you truly measure the quality of the customer experience you are delivering? How do you know you’re getting better? Amazon and Google know that the answers to these questions involve helping customers get stuff done as quickly as possible. Task completion gets you in the right ballpark, but it is speed that wins you the game of excellent customer experience. This keynote stresses how the relentless pursuit of customer convenience drives customer loyalty, retention, and revenue growth. Learn how to speed to success by measuring your results.

Presented by: Gerry McGovern

A101: Building Cross-Platform Conversational User Experiences

10:15 – 11:00

New conversational dialogue platforms are based on state-ofthe- art machine learning and artificial intelligence techniques. The platform learns from examples provided by developers and end-user conversations to continuously improve user experience. These solutions are built across platforms, allowing companies and organizations to instantly expand their reach to new audiences. We also showcase innovative use cases demonstrated from early adopters in this rapidly growing area.

Presented by: Ilya Gelfenbeyn

B101: Achieving Digital Transformation Through Intelligent Virtual Assistance

Track B: DIGITAL TRANSFORMATION – Monday 24 April 
10:15 – 11:00

This session describes how to engage and guide clients through digital transformation. What are the costs, security implications, and other special considerations when designing virtual assistants? How can you architect a configurable and reusable virtual assistant pipeline using open source tools and APIs? How can you enhance virtual assistant intelligence with search, recommendation, and semantic technologies? See a live demonstration of an omni-channel digital campsite booking experience. The demo seamlessly moves from the Amazon Echo to a web-based chatbot and then to a mobile phone assistant.

Presented by: Sumeet Vij

C101: Conversational Interfaces & the Future of Customer Interaction

Track C: VIRTUAL ASSISTANTS – Monday 24 April 
10:15 – 11:00

Conversational interfaces are quickly becoming an essential component of every service and product. This session presents approaches for emerging UX challenges in its conversational agent platform, the opportunities in the customer interaction space, and the future of conversation agents. Vemuri introduces the Google Assistant, its various surfaces (Google Home, Pixel), and the vision behind it. He then discusses designing for conversational experiences, and how the Assistant allows for omni-channel customer support.

Presented by: Sunil Vemuri

D101: PANEL: Can You Trust Them?

Track D: NEXT BIG THING – Monday 24 April 
10:15 – 11:00

We examine privacy and ethics for emerging automation. When you accept assistance, whether it be from a banker, mechanic, or fish salesman, there is always an open question of who gains what from the transaction. It is important to assess whose side your automated assistant will take. Military drones and driverless vehicles already participate in life-and-death decisions. Soon, they’ll be joined by social robots providing services such as eldercare and childcare. Should we be concerned?

Presented by: Moshe Yudkowsky, Judith Markowitz, Jordan Cohen, David Attwater