We look at how digital transformation is affecting call centers and how speech technology is helping to meet the new needs that are emerging. We cover key issues such as the following: Who still calls enterprises and why? Is self-service in the IVR going away and if not, why not? Why are greater and greater demands being placed on natural language in the IVR?

This is a brainstorming session for creative and useful new speech applications. Attendees can suggest all kinds of applications including speaking with IoT, speaking to your car, speaking to within VR apps, etc. The list of possible apps could be useful for planning future products. Come and help define the future of our industry.

Suppose we switch our mindset of new self-service projects from IT-centric to people-centric and include them in our workforce management, training, mentoring, and planning efforts? What if you treat them as digital employees that are only a new hire once, trained like their human counterparts, and thus perform constantly better over time, never get sick, work 24/7, never leave? The ROI becomes tremendous, and the resulting customer experience, superior. This talk explores what this transformation would mean for businesses and vendors alike.

Recent work has applied advanced NLP, machine learning, graph algorithms, and ontology work to automate transcripts for audio/video content. Transcripts are parsed and indexed for search and recommendations and also automatically summarized for editorial use. In particular, a human-in-the-loop design pattern, based on Jupyter notebooks and other open sources, was applied to improve results—blending AI apps with human expertise. Those results in turn have been used to develop conversational interfaces (Alexa, etc.) for speech applications and intelligent assistants that make learning materials more accessible. This talk presents how AI apps in media help resolve important issues for both editors and consumers.

Learn how biometrics uniquely balances security and convenience while bringing a new level of personalization to customer service. Discover ways in which AI can help create biometric watchlists that spot abnormal activities as they happen. Compare the features and benefits of various types of biometrics. Explore use cases for biometrics and real-world examples.

From data breaches to the latest phishing scam, are you prepared to ensure your customers’ data is protected? Baeten reviews methods used to authenticate callers in contact centers. Learn about popular methods (PINs and passwords), current recommendations (voice biometrics, using multiple factors …), and what the future of authentication will look like (behavioral biometrics, predictive analytics …). Are you prepared to protect your customer?

Learn how Theatro is transforming retail by equipping tens of thousands of hourly retail associates with a voice-controlled personal assistant, enabling them to communicate with one another, with store management and with backend systems. Our mobile virtual assistant solution provides a software suite of productivity and communication applications through a SaaS (Software as a Service) offering designed to optimize employee, sales, and operational performance.

Conroy discusses how Finn.ai developed a production-ready, virtual banking, and conversational agent in Facebook Messenger. He deep dives into the decisions around building conversational agents in-house vs. working with existing vendors: what to consider, what to look for, and constraints on both ends. Learn what tooling is available, how to leverage natural language processing and big data in a functional capacity. Conroy makes recommendations about how to build such an environment.

As designers, we strive to discover the true problems and opportunities to solve, but often we don’t get the chance. Learn how we use techniques such as usability street intercepts, interviews, and mental modeling to seek out real user problems and rapidly learn directional clarity before starting to design solutions. Since early design research is grounded in real people, directional insights can also be used to alter business scope. Often, this results in a happier business partner and a satisfied customer.

Because the augmentation of reality will take many forms, it’s imperative that we integrate vision, touch, hearing, and speech into new sensing environments to create a truly natural, human experience. This session covers the relationship between technology and our human senses and offers insights to those working on AR projects or foundational, IoT frameworks that may help AR emerge as a human senses-led technology that people will actually welcome and enjoy.

Voice Biometrics Group has developed a noise modeling system based on deep learning algorithms. Soufleris describes the challenges of using prior noise filtration techniques and why newer, learning-based algorithms are able to perform better by cutting EER by 40% or more. He discusses how these techniques can be applied to gender classification, emotion detection, channel identification. Although highly technical in nature, this presentation is framed in common, everyday terms that business decision-makers can understand.

Fraud countermeasures are one of the most relevant topics today. Many companies rely on voice biometrics to obtain natural and usable identity verification services. However, security breaches could be caused by recordings, audio manipulation, and even synthetic voices. Learn about latest development in biometric countermeasures systems and advanced spoofing attacks detection with the most recent deep learning training schemes.

Does your organization need a strategy around voice? (Here’s a hint: The answer is, “Yes.”) What should that strategy be? Should you build an Alexa Skill or Google Action, or do something else entirely? This hands-on overview workshop looks at the problem through three different lenses: technology, design thinking, and marketing. First, tech. What’s involved in a voice enabled design, and what are companies doing today? Second, design thinking. Start with a user-centered view of the world—what does it look like when you throw voice into the mix? Third lens: marketing. What does search engine optimization look like in a world without “results” pages? How should your brand sound? This session gets you thinking about these questions and gives you the tools to make intelligent decisions about your organization and voice.

Deep learning is systematically stomping out old algorithms in multiple fields, including speech recognition, by delivering breakthrough accuracy. Combined with big data, these methods are advancing research in finance, images, self-driving cars, advertising, spoken language, and games. This tutorial will cover new formulations of machine learning with a focus on DNNs for speech recognition and natural language processing. The session includes demonstrations and hands-on exercises. We recommend that participants bring a laptop. Attendees gain an understanding of DNN fundamentals, how they are used in acoustic and language modeling, the emergence of easy-to-use software tools, and where deep learning appears to be headed. Recent advances in deep learning, speech recognition fundamentals, how DNNs work, and why they are so accurate are all discussed.

Google Assistant allows users to engage with information and services through devices such as Google Home, Android smartphones and iPhones, and, ultimately, a wide range of other smart devices. Creating a conversational chatbot brings certain challenges. This tutorial begins by exploring issues of conversation design and then outlines the various tools available, such as Actions on Google, which supports the building of apps for Google Assistant; API.AI (Dialogflow), a tool for defining the natural language understanding and dialogue components of a conversation; Google templates, an alternative way to quickly create a conversational app; and Actions Simulator, a tool for testing the chatbot. The main part of the tutorial provides a hands-on demonstration of the tools.

Participants are expected to bring a laptop for use during this workshop to develop a sample chatbot for Google Assistant. Laptops will not be provided.