Show Notes
Explainable VUI
"The Future is Spoken" presents Dr Maria Aretoulaki as this week's guest. Maria is a Voice First Veteran, having been designing Voice User Interfaces (VUIs) since 1996, long before Voice Assistants, but also before telephone self-service and Speech IVRs were mainstream. She got into Voice Design through a Post-Doc in Spoken Dialogue Management for Speech Recognition applications, after getting a PhD and an MSc in NLP and Machine Learning and, earlier, a BA (Hons) in Linguistics & English.
She has held Senior VUI | Voice Design and Technical Project Management positions both in Academia and in Industry in the UK and Germany. In 2008, she founded her own VUI & Conversational Design Consultancy, DialogCONNECTION Limited. In that time, Maria has provided her VUI Design and Speech Recognition expertise to organizations in Europe, the US and Asia, including APPLE, SAMSUNG, VODAFONE, SKY, TALK TALK, EMIRATES NBD, the NHS and the European Commission. Her Voice designs, call flows, dialogue scripts and tuning recommendations have saved her clients up to $10 million annually.
Originally from Greece, Maria has spent the last 30 years between the UK and Germany, and has provided multilingual and culturally appropriate Voice Design services for English, German, French, Italian, Spanish and Greek.
Starting with their own experiences, Maria and Shyamala discuss what Explainable VUI Design is and give some insightful advice to aspiring Conversational Designers.
Tune in now!
Conversation Highlights:
[00:25] From Linguistics to NLP to VUI Design
- Maria originally studied Linguistics and English Literature in Greece, so she naturally wanted to go and study and work in the UK.
- She was looking for Sponsorship for her Masters, when she bumped into the field of Machine Translation and NLP.
- During her PhD studies in 1993, she discovered the world of Artificial Neural Networks and got fascinated by their potential and decided to apply them to Automatic Text Summarisation.
- It was through a Post-Doc in Spoken Dialogue Management for Speech IVRs that she got into the world of Voice and Speech Recognition back in 1996. From then on, she has been a VUI Designer!
[07:20] SIRI comes into play!
- Maria explains how the iPhone was like having a full computer in our pockets and how SIRI was the beginning of a new era, making Speech Recognition and Voice mainstream.
- She feels very proud about the Voice field, which she considers like her "baby" growing up to be an adult!
[09:40] Explainable VUI
- Maria coined the term "Explainable VUI" amid the myriad of Voice applications and Voice Assistant skills / actions / capsules designed by programmers or marketing people.
- "Explainable VUI" means to design a Human-Computer interface bearing in mind both the complexities and imperfections of human language and the limitations of the technology (ASR / speech recognition / NLP).
- A lot of her work with various companies and organisations creating VUI Designs from scratch or reviewing existing ones is carefully crafting system prompts.
- She stressed the importance of knowing how the background technology works.
[20:23] Balancing UX with discoverability of new features.
[22:16] How many menu options can a user take?
- Voice helps the user to quickly bypass a big chunk of the menu tree, if they know what they want, especially power users. Menu options are for newbies or people who are not sure what to ask for.
[24:05] Challenges of VUI vs GUI
- Maria elaborates on the different types of challenges that Voice interfaces have compared to graphical interfaces.
- Voice can empower and engage many more disenfranchised people, if designed right.
- She also explains how designers can address inclusivity in their conversation design, without necessarily showcasing the shortcomings of the interface.
[39:17] The importance of Data
- Maria emphasises the need for a data-driven approach in Conversational Design.
- Conversational designers certainly need to spend a lot of time thinking about the dialogues, but there are so many other factors to consider in designing a good dialogue system that enjoys high acceptability and adoption rates.
- Designing dialogue flows for Voice or Chat is not the same as writing catchy mottos or gripping stories
[47:20] Designing for Listenability rather than Readability
- Chatbots vs Voicebots and Voice Assistants
- Maria elaborates on how to ensure designing for listeners rather than for readers.
- She stresses the need to provide concise but also clear and unambiguous information.
- Voice input presents a great deal more challenges than Chat input, which is far less ambiguous.
[52:14] Must Listen
- Maria's pieces of advice for aspiring Conversational Designers and people new in this field on how to start, learn, get ahead, and flourish.
Learn more about Maria here:
- Her company website, DialogCONNECTION Ltd http://dialogconnection.com/
- Her LinkedIn https://www.linkedin.com/in/aretoulaki-
- Her Twitter https://twitter.com/dialogconnectio and https://twitter.com/ar3toul4ki
- Her Blog https://aretoulaki.wordpress.com/
If you enjoyed this episode of The Future is Spoken, make sure to subscribe to our podcast.
Follow Shyamala Prayaga at @sprayaga