Dustin and Kane are joined by Patricia Scanlon, CEO SoapBox 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 kids

Imagine 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 Scanlon

Patricia Scanlon is the founder and CEO of SoapBox 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.

Links

Get a free 90 trial of the SoapBox Labs API:

Visit soapboxlabs.com

Email [email protected]

Hosted on Acast. See acast.com/privacy for more information.

Deborah Harrison was the very first writer on the Cortana team and defined the personality of Microsoft's digital assistant that is used on over 400m surfaces globally.

In this talk, we chat to Deborah about the importance of personality and persona in conversational experiences, and the critical responsibility of ethical design.

Links

Follow Deborah on Twitter

Hosted on Acast. See acast.com/privacy for more information.

Voice search is growing. As smart speaker adoption increases and people use the voice assistants on their phones more and more, voice is playing an increasing role in more customer journeys.

But what's your share of voice? How often does your company 'rank' for the search terms you'd like to rank for?

Amazon and Google are tight-lipped about voice search volumes and don't offer any way of tracking voice search performance for websites, skills or actions.

Thankfully, Andy Headington and his team at Adido, has created a tool that lets you do just that.

In this episode, we speak to Andy about how you can measure your share of voice, and how you can find ways of identifying insights that will enable you to improve you voice search performance.

Links

Try Share of Voice 

Hosted on Acast. See acast.com/privacy for more information.

What is speech recognition and how does it work?

Automatics speech recognition (also known as ASR) is a suite of technology that takes audio signals containing speech, analysis it and converts it into text so that it can be read and understood by humans and machines. It's the technology that makes voice assistants like Amazon Alexa able to understand what a user says.

There's obviously a whole lot more to it that than, though. So, in today's episode, we're speaking to one of the most knowledgable and experienced speech recognition minds the world has to offer, Catherine Breslin, about just exactly what's going on under the hood of automatic speech recognition technology and how it actually works.

Catherine Breslin studied speech recognition at Cambridge, before working on speech recognition systems at Toshiba and eventually on the Amazon Alexa speech recognition team where she met the Godfather of Alexa, Jeff Adams. Catherine then joined Jeff at Cobalt Speech where she currently creates bespoke speech recognition systems and voice assistants for organisations.

In this episode, you'll learn how one of the fundamental voice technologies works, from beginning to end. This will give you a rounded understanding of automatic speech recognition technology so that, when you're working on voice applications and conversational interfaces, you'll at least know how it's working and then be able to vet speech recognition systems appropriately.

Presented by Sparks

Sparks is a new podcast player app that lets you learn and retain knowledge while you listen.

The Sparks team are looking for people just like you: podcast listeners who're also innovative early adopters of new tech, to try the beta app and provide feedback.

Try it now at sparksapp.io/vux

Hosted on Acast. See acast.com/privacy for more information.

Voice shopping on Alexa and Google Assistant smart speakers is a $2bn market today, and is forecast to explode. I've wrote about the potential of voice shopping for the Harvard Business Review last year, but things are starting to pick up.

According Amazon's Patrick Gauthier, 20% of Americans are ready for voice shopping now, and 39% of all Americans will complete some part of their purchase journey via voice by 2022.

And while it might not generate a huge percentage of sales today, the learnings that you'll gather through observing and collecting data on how customers are interacting with your brand, will be worth its weight in gold when the volcano erupts. 

Presented by Sparks

Sparks is a new podcast player app that lets you learn and retain knowledge while you listen.

The Sparks team are looking for people just like you: podcast listeners who're also innovative early adopters of new tech, to try the beta app and provide feedback.

Try it now at sparksapp.io/vux

Introducing Shilp Agarwal, CEO, Blutag

Our guest today is Shilp Agarwal, serial entrepreneur and co-founder of Blutag, the voice shopping platform making it possible for retailers to sell on Alexa and Google Assistant with ease. 

Shilp talks us through how he sees the voice shopping landscape today, how it's changed over the last two years, and why it's going to explode in the next 18 months.

Some highlights for retailers considering Alexa for voice shopping

Selling via Alexa skills can have an ROI and offer some key learnings. Fresh Direct increased its shopping cart size by 12% with its Alexa skill, powered by Blutag.

But the ROI is about more than sales. You can get ahead of your competition by excelling in customer experience, offering voice options at different stages of the customer journey. From product research and consideration, through ordering and delivery tracking, right through to post-sales.

And you don't need to be all things to all people straight away. Instead, try focusing on smaller parts of the shopping experience that'll help you get moving quickly, offer some value immediately and learn from your users. Things like repeat purchases or delivery checking are ideal.

One thing is for sure, voice shopping is on the horizon and getting ahead now will put you in a great position.

Links

Visit blu.ai 

Hosted on Acast. See acast.com/privacy for more information.

Corona virus hits voice as Google removes coronavirus actions, Spotify looks like it's releasing a voice assistant and Jovo lets you build voice assistants everywhere.

Presented by Sparks

Sparks is a new podcast player app that lets you learn and retain knowledge while you listen.

The Sparks team are looking for people just like you: podcast listeners who're also innovative early adopters of new tech, to try the beta app and provide feedback.

Try it now at sparksapp.io/vux

Stories discussed in this episode

Google reject corona virus action

Spotify might be releasing a voice assistant

Jovo v3, build voice assistants and deploy them everywhere

Jovo Linkedin vlog 

Google Read It

Google Read It Linkedin vlog

Alexa, the OS

Live broadcasting on Alexa with the Food Network

The end of Alexa Skills?

 

Hosted on Acast. See acast.com/privacy for more information.

The Food Network aims to the be Peloton of cooking with live video broadcasting on Alexa. Director of Technology and Emerging Platforms at Discovery Inc., Tim McElreath, joins us to share how.

Presented by Sparks

Sparks is a new podcast player app that lets you learn and retain knowledge while you listen.

The Sparks team are looking for people just like you: podcast listeners who're also innovative early adopters of new tech, to try the beta app and provide feedback.

Try it now at sparksapp.io/vux

Live video broadcasting on Alexa

The Food Network are working closely with Amazon to build out features for live video broadcasting on Echo Show devices and aims to be the Peloton of cooking.

Tim McElreath shares the story of what the Food Network is up to and how they see voice assistants such as Amazon Alexa shaping the future of engagement and content distribution in future. 

Through the Food Network app, you can pay a subscription to access premium content such as in-app live interactive cooking shows. This is what Tim is bringing to Alexa. Live cooking demonstrations with the ability for the audience to ask questions to Alexa and have those questions fed through to the presenter to be answered live.

We also discuss the process of making live broadcasting happen and how it's being built as first party functionality. That means that the Food Network aren't building a skill for this. Instead, they're sending a feed and metadata to Amazon for Alexa to distribute it directly. Is this a sign of the future? Moving away from skills and towards feeding Alexa content with metadata directly?

The Food Network aims to own the kitchen and Alexa is a big part of that. This episode will show you how Tim and his team are pursuing such goals and will have you thinking about how you can do the same.

Links

Try the Food Network skill (US only)

Connect with Tim on Twitter

 

Hosted on Acast. See acast.com/privacy for more information.

Jon Bloom, Senior Conversation Designer at Google, joins us to share what a conversation designer does at Google, as well as some conversation design techniques used at Google, such as 'grounding strategies'. 

Presented by Sparks

Sparks is a new podcast player app that lets you learn and retain knowledge while you listen.

The Sparks team are looking for people just like you: podcast listeners who're also innovative early adopters of new tech, to try the beta app and provide feedback.

Try it now at sparksapp.io/vux

Conversation design and grounding strategies

Conversation design is one of the core skillsets required to create engaging and effective voice and conversational experiences. UX Mag recently wrote about how the role of conversation designer will be one of the fastest growing UX roles in 2020.

But what exactly is conversation design? And what does a conversation designer actually do?

This week, we're joined by Jon Bloom, Senior Conversation Designer at Google to find out.

We discuss the role, what's involved, Jon's prior experience, the resurgence of enthusiasm in the voice community, as well as some conversation design techniques you can use to start creating engaging conversational experiences.

Conversation design techniques

One of the highlights of the conversation is Jon's take on errors.

Within the conversation design community, most people talk about 'error recovery', which is recovering from situations in a conversation where things go wrong. For example, if a user asks for a pizza, and the system says 'what flavour', what happens when the user says a flavour that the system doesn't have? Or if the system mishears the user?

Recovering from these situations is typically known as 'error recover', but Jon's perspective is different and refreshing.

Jon mentioned that within all conversations, there are no such thing as errors. There is simply 'grounding'.

Grounding includes anything and everything the two people do within a natural conversation in order to ensure understanding.

For example, if a user asks for a hotel room for Tuesday, the system might confirm with 'Here's the rooms I found for Tuesday'. Confirming that it heard Tuesday is a form of grounding.

In the pizza example, where the user asks for a flavour the system doesn't have, the system might respond with 'I'm sorry, we don't have Hawaiian, but we do have farmhouse'.

These aren't 'errors', they're natural parts of human conversations and the things we do to ensure both parties are on the same page.

We get into some great detail on this with Jon, as well as plenty more conversation design techniques.

About Jon Bloom

Jon is a veteran in the conversation design space, with decades of experience working in speech recognition systems, conversational UX and natural language-based human-computer interaction.

He created the interface design process for the well renowned dictation system Dragon Dictation by Dragon Systems, before moving to SpeechWorks (acquired by Nuance) to work on conversation design for IVR phone systems and in-car speech recognition systems.

Jon then worked at Synchronoss Technologies working on analysing and improving speech recognition systems for IVR phone systems, then moved back to Nuance as a Senior User Interface Manager.

Jon currently works predominantly on the Google Assistant and is responsible for making interactions and experiences on Google Assistant as intuitive and as user friendly as possible.

Links

Follow Jon on Twitter

Designing Voice User Interfaces by Cathy Pearl

Voice User Interface Design by James Giangola

Google's conversation design guidelines

Google's 'error' recovery guidelines (The irony isn't lost on me that Google has called this 'errors', rather than 'grounding'. Although this does include genuine system errors such as speech recognition issues)

Hosted on Acast. See acast.com/privacy for more information.

Maaike Coppens returns to share how you can go from zero to hero in one voice design sprint. From nothing at the beginning to a a validated use case and prototype at the end, with fun in the middle. 

Presented by Readspeaker

Readspeaker is a pioneering voice technology company that provides lifelike Text to Speech (TTS) services.

Whether you're needing a TTS voice for your IVR system, voice application, automobile, robot, public service announcement system, website or anywhere else, Readspeaker have you covered.

They've been in the TTS game for over 20 years and have 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.

If you're in the market for any form of TTS technology, check out Readspeaker today.

In this episode

You can't design conversations without having them. This is Maaike's core message, and it's true. That's why the voice design sprint was born. 

Taken from the core principles behind the book, Sprint, by Google's Jake Knapp, and the Google voice sprint methodology, Maaike has adapted and created a version of the design sprint that's perfect for voice. 

Everyone speaks differently and approaches a conversation from a different starting point. The art of conversation design is to create an experience that works for all and is personalised where it needs to be. 

However, sometimes we're limited by the technology we're working with. 

For people who're new to conversation design or voice design, it's often thought that conversations with voice assistants just happen and that the sky is the limit. You know, because the 'AI' will handle everything. 

In reality, that's not the case and there's a certain amount of education and grounding required to show the limitations of the technology and what a realistic conversation looks like. 

Enter the voice design sprint

Through a series of 'serious games' and interactive exercises, that's exactly what this voice design sprint does. 

In this episode, Maaike takes us through the voice design sprint workshop format and runs through the exercises so that you can try them in your own voice design sprints.

Links

Join Maaike on LinkedIn

Maaike's website

Design sprint website

Sprint by Jake Knapp

The Google Voice Design Sprint

Transcreating voice experiences with Maaike Coppens

Grice's Maxims

Hosted on Acast. See acast.com/privacy for more information.

VaynerMedia are one of the leading global digital agencies. Director of Innovation at VaynerSmart, Claire Mitchell, joins us to share how VaynerMedia approach voice, as well as sharing some insights on situational design and sound design.

Listen on:

Apple podcasts | Spotify | YouTube | Overcast | CastBox | Spreaker | TuneIn | Breaker | Stitcher | PlayerFM | iHeartRadio

Presented by Readspeaker

Readspeaker is a pioneering voice technology company that provides lifelike Text to Speech (TTS) services.

Whether you're needing a TTS voice for your IVR system, voice application, automobile, robot, public service announcement system, website or anywhere else, Readspeaker have you covered.

They've been in the TTS game for over 20 years and have 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.

If you're in the market for any form of TTS technology, check out Readspeaker today.

In this episode

What is situational design? What does it mean for the creation of your voice application? Claire Mitchell of VaynerMedia joins us in this episode to find out.

In this episode, we take deep dive into situational design and how you can apply it to your voice first applications, Alexa skills or Google Assistant actions.

Claire also has a passion for sound design and identifies this as an area of focus for voice in 2020. We speak to Claire about how VaynerMedia have used effective sound design to improve VUX and Claire also shares some examples of use cases and applications where sound design is being used to great effect.

We also have a general chat about voice at VaynerMedia and Claire's experience in voice technology and smart home VUI overall.

Links

Join Claire on Linkedin

Situational design

The Audible Past

Bloomberg Sonificiation

The Structure of Scientific Revolutions

Fritz Kahn

Hosted on Acast. See acast.com/privacy for more information.