Share

VUX World

The practical voice podcast

Learn how to implement voice first strategy and create world-class voice experiences with VUX World. Every week, we speak to industry thought leaders and practitioners on the three core pillars of voice: strategy, design
Latest Episode5/26/2020

Designing natural conversations with IBM's Bob Moore

Magic happens when you take patterns and systems of nature and apply them to solve human problems.✈️ Aeroplane wings are inspired by birds🚗 Wet tyre treads have been inspired by the toe pads of tree frogs💡 LED bulbs can be made more efficient by mimicking the scales on a Firefly’s abdomen📸 Canon cameras imitate the structure of a moth’s eye to reduce lens flare🚞 High speed trains in Japan were based on a Kingfisher’s beak. They use 15% less electricity and are 10% fasterWhat happens when you take a conversational analyst and have them apply natural, human conversation patterns and techniques to conversation design and conversational AI?Can we create more engaging human computer interaction? Can we provide better, more natural customer experience?In this episode, you'll learn how to design conversations properly, based on those that have conversations properly: humans.Our guest, Bob Moore, spent over 20 years in Silicon Valley research labs working with the likes of Xerox PARC, Yahoo! Research and IBM ARC, studying conversations and analysing the natural patterns that occur. He has a Ph.D. in sociology, is a trained as a conversation analyst and the author of Conversational UX Design:A Practitioner's Guide to the Natural Conversation Framework.LinksConversational UX Design IBM Research AlmadenMoore, Robert J. and Raphael Arar. 2019. Conversational UX Design: A Practitioner's Guide to the Natural Conversation Framework. Association for Computing Machinery, New York. DOI: 10.1145/3304087.Available atAmazonandMorgan & Claypool.
5/18/2020

What is text-to-speech and how does it work with Niclas Bergström

Every voice assistant needs three core components: Automatic Speech Recognition (ASR), Natural Language Understanding (NLU) and Text-to-Speech (TTS). We've already coveredwhat Automatic Speech Recognition is and how it workswith Catherine Breslin and in this episode, we're covering the latter, text-to-speech.To guide us through the ins and outs of TTS, we're joined by Niclas Bergström, a TTS veteran and co-founder of one of the largest TTS companies on the planet, Readspeaker.Text-to-speech is the technology that gives voice assistants a voice. It's the thing that produces the synthetic vocal sound that's played from your smart speaker or phone whenever Alexa or Siri speaks. It's the only part of a voice assistant that you'd recognise. The other core components, ASR and NLU, are silent.And, given how we're hard wired for speech - a baby can recognise its mother's voice from the womb - how your voice assistant or voice user interface (VUI) sounds is one of the most important parts of it.A voice communicates so much information without us necessarily being aware. Just from the sound of someone's voice, you can infer gender, age, mood, education, place of birth and social status. From the sound of someone's voice, you can decide whether you trust them.With voice assistants, voice user interfaces, or any hardware or software that speaks, choosing the right voice is imperative.Some companies decide on a stock voice. One of Readspeaker's 90 voices or perhaps Amazon Polly. Others create their own bespoke voice that's fit for their brand.We see examples ofLyrbird's voice cloningand we hear Alexa speak every day, so it's easy to take talking computers for granted. Because speaking is natural and easy for us, we assume that it's natural and easy for machines to talk. But it isn't.So in this episode, we're going to lift the curtain on text-to-speech and find out just exactly how it works. We'll look at what's happening under the hood when voice assistants talk and see what goes into creating a TTS system.Readspeakeris a pioneering voice technology company that provides lifelike Text to Speech (TTS) servicesfor IVR systems, voice applications, automobiles, robots, public service announcement systems, websites or anywhere else.It's been in the TTS game for over 20 years and has in-depth knowledge and experience in AI and Deep Neural Networks, which they put to work in creating custom TTS voices for the world's biggest brands.LinksVisitReadspeaker.comto find out more about TTS servicesAndReadspeaker.aifor more information on TTS research and samples
5/14/2020

Voice technology and music with Dennis Kooker and Achim Matthes

Music has been the top use case on smart speakers pretty much from the beginning. Having any song you like at your beckoning call makes playing music around the house easier than ever. And households that play music out loud are, apparently,happier households.It doesn't require too much thought, either. So, discoverability isn't as much of a challenge as with skills, actions and services. If you want to play some Michael Jackson, just ask.Having said that, music consumption habits are advancing. According toPandora, more people are listening to up-beat, exercise music during lockdown, presumably to exercise to given the gyms are shut. And more people are listening to more ambient music, too, as well as child friendly playlists. People spending time at home and using their music service to relax and entertain the kids respectively.And there's a growing trend moving away from listening to artists and towards listening to playlists. Random compilations of different tunes grouped around a theme. And with smart speakers, we're seeing an insight into people's contexts with the music they ask to play. For example 'play BBQ music' might not be something you'd try and find on Spotify, but you might ask for it from your smart speaker.In the age of playlists, mood music and music on demand, how does a record label make sure that its catalogue of music is found and played on smart speakers? Well, that's what we're going to find out in this episode.In this episode: voice strategy at Sony MusicWe're joined by Dennis Kooker, President, Global Digital Business and US Sales, and Achim Matthes, Vice President, Partner Development, at Sony Music Entertainment. Dennis and Achim walk us through how Sony Music is thinking about voice, some of the behavioural trends they're seeing play out, how they make sure that, when you ask for a Sony Artist song, you get what you've asked for, what's involved in music discoverability, what trends they're seeing and where they see music and voice heading in future.
4/30/2020

Voice technology for kids with Dr. Patricia Scanlon

Dustin and Kane are joined by Patricia Scanlon, CEOSoapBox Labs, to discuss how its specialist speech technology for kids is being used and scaled across the globe to help kids learn to read and more.In this episode: voice tech for kidsImagine being able to have your child read to an iPad and have it tell them how they’re doing. Whether they’re pronouncing the words right and encouraging them to improve.Imagine, as a parent or teacher, being able to report on different child’s progress so that you can focus on the real areas that need improving.Well, this is what Soapbox Labs enables you to do with its specialist speech technology which you can use to build bespoke applications specifically for kids.You might be wondering 'why would I need speech technology specifically for kids?' Well, kids have totally different voices to adults. Their pitch is higher, they don't always pronounce words properly and it changes across the ages. A 5 year old's voice is different to a 10 year old's voice.Most of the speech recognition systems you'll be familiar with are trained on adult voices and don't tend to work too well for kids voices.In this episode, we expand on this and more with a deep discussion on just why voice technology for kids is so important, how the solution was created, what makes it unique and how you can use it to create life changing applications that help kids all over the world learn and entertain themselves.We discuss use cases in education, such as learning to read or learning a new language, as well as leisure, such as speech recognition in toys.After listening or watching this episode, you'll not only be equipped with the knowledge you need to create effective voice applications for kids, you'll also have a new appreciation for just how important this kind of technology is, what kind of opportunity exists in creation educational solutions for kids, but also just how important all of this is.About Patricia ScanlonPatricia Scanlon is the founder and CEO ofSoapBox Labs, the award winning voice tech for kids company. Patricia holds a PhD and has over 20 years experience working in speech recognition technology, including at Bell Labs and IBM.Patricia has been granted 3 patents, with two pending. She is an acclaimed TEDx speaker, and in 2018 was named one of Forbes "Top 50 Women in Tech" globally.In 2013, inspired by the needs of her oldest child, Patricia envisioned a speech technology to redefine how children acquire literacy. She has successfully raised multiple rounds of both public and private funding to bolster research and product development, and her technical approach has been independently validated by the world's top three academic authorities on speech recognition.SoapBox Labs is based in Dublin and has a world class team of 22 employees.LinksGet a free 90 trial of the SoapBox Labs API:Visitsoapboxlabs.comEmailhello@soapboxlabs.com