Voice Tech Podcast

Latest Episodes:

Sound Recognition - Dr. Chris Mitchell, Audio Analytic Apr 28, 2019

Show notes

Dr Chris Mitchell is the CEO and Founder of Audio Analytic, who develop sound recognition software that adds context-based intelligence into consumer technology products. In our conversation, you'll learn what the state of the art sound recognition systems can do, the types of sound events that are typically recognised, which consumer products they're integrated into, and the many benefits and new possibilities the technology affords to developers and users.

We discover the difference between sound recognition and speech recognition, how sound recognition provides the all important context for voice enabled devices to make the right decisions, and how smart devices can take advantage of this contextual knowledge. Then we dive into some of the technical details of how it all works, including 'better than real-time processing', edge computing vs the cloud, the need to train custom acoustic models, and how these machine learning models can run on low-resource devices like headphones using TinyML. Chris briefly explains the process of integrating the AI3 framework into your products, then we tackle the all important question of data privacy and security.

Many of the smart devices of future will rely on sound recognition to understand the context of their environments. Chris and his team are at the cutting edge of the sound recognition field and are long-time experts in the domain, so there's no better person to introduce us to this important technology.

Links from the show:

Audio Analytic: https://www.audioanalytic.com
Hive Hub case study: http://bit.ly/2IOlA9E

Sponsors:

Dabble Lab: https://youtube.com/dabblelab
Manning books: https://www.manning.com 40% off all books code: podvoicetech19
Voice-Connected Home 2019: https://bit.ly/2IZuVwc, 20% discount code: VoiceTech

Find us here:

★ Support this podcast on Patreon ★

Voice Actors & Synthetics - David Ciccarelli, Voices.com Apr 14, 2019

Show notes

David Ciccarelli is the CEO of Voices.com, the online marketplace where brand managers and marketers discover, audition and hire professional voice actors. In our conversation, you'll learn all about how to find and hire a voice actor to represent your brand in marketing campaigns or for use in voice development projects, how projects are priced, and what rights you have to use the audio you purchase.

We discover why personas are the most effective common language to describe voices. We also hear samples of the state of the art in synthetic voices, and learn when and why to choose a synthetic voice over a human actor. We also discuss the reasons for the recent boom in voice content and services, and how voice in all forms, from audiobooks to podcasts, is the ideal medium for today's highly mobile, permanently connected population.

David is a seasoned professional in the voice space with decades of experience and advice to share, so whatever your interest in voice you're sure to get a lot of value from this conversation.

Links from the show:

Voices.com site http://bit.ly/2Iy8Tiq
Voices.com future market report http://bit.ly/2IDuOor
Voicesummit.ai conference http://bit.ly/2IuZ04Y
Voice of the car conference http://bit.ly/2IuTsY5
Librivox audiobooks http://bit.ly/2IuZ44I
Jargon SDK http://bit.ly/2IxZzL5
VocalID custom voices http://bit.ly/2Is3DwF

Sponsors:

Dabble Lab: https://youtube.com/dabblelab
Manning books: https://www.manning.com 40% off all books code: podvoicetech19
Voice-Connected Home 2019: https://bit.ly/2IZuVwc, 20% discount code: VoiceTech

Find us here:

★ Support this podcast on Patreon ★

Biometric Authentication - Alexey Khitrov, ID R&D Mar 30, 2019

Show notes

Alexey Khitrov is President at ID R&D, who increase the security of interactions with digital products such as conversational interfaces using voice authentication and behavioural biometrics. Their products add hands-free, zero-authentication to any voice enabled device, heralding a new era in frictionless, ubiquitous computing services.

We discuss how voice biometrics move us towards a future where we communicate with technology just like we communicate with our friends. Alexey gives us an overview on the state of voice authentication today, who's using it, and its limitations. We also cover the technical features of voice authentication, such as modal enrichment for continuous enhancement of the authentication accuracy. We hear about the design challenges faced when introducing zero-authentication to your application, and get advice for implementing this technology into your own voice apps.

To wrap things up, we look ahead to the voice technology features we are likely to see emerge in 2019 and beyond, and tackle the risks around data privacy, security, and the evolving arms race between hackers and software security firms. This episode is one the most interesting conversations I've had doing this podcast and it's a real pleasure to be able to share it with you.

Links from the show:

ID R&D homepage: https://idrnd.net/
ID R&D demo you can try: http://bit.ly/2I3UnPc
ID R&D demo on Youtube: https://youtu.be/AdMzny1m2zE
ID R&D in call centres: http://bit.ly/2HY0XXn
ID R&D company profile: http://bit.ly/2HY0ILX

Sponsors:

Dabble Lab: https://youtube.com/dabblelab
Manning books: https://www.manning.com 40% off all books code: podvoicetech19
Dashbot Super Bot Conference 2019: https://sb2019.dashbot.io, 25% group discount code: voicetech
Voice-Connected Home 2019: https://bit.ly/2IZuVwc, 20% discount code: VoiceTech

Find us here:

★ Support this podcast on Patreon ★

Voice Search Results - Dustin Coates, Algolia Mar 16, 2019

Show notes

Dustin Coates is the Voice Search Go-to-market Lead at Algolia, a Search-as-a-Service provider based in Paris, France. Algolia processes up to 4 billion searches a month for over 6500 client products, including big names such as Twitch and NPR.

In our conversation, you'll learn all about the 4 pillars of a search system; the indexing of data, relevance configuration, search queries, and the display of results. We discuss the nuances of voice search, context dependent searches, and the differences between searching on mobile vs a smart speaker. We also cover the challenges of talking to websites, discovery vs search, and much more.

Dustin shares his advice for voice search developers, including how to integrate voice search into your apps, and the most useful tools and technical resources. Dustin's deep technical experience really shines though in this interview, as one of the few true voice search experts.

Links from the show:

Dustin's book: http://bit.ly/2VZ2U9A
Dustin's dabble lab tutorial: http://bit.ly/2W3kRnq
VScode Alexa plugin: http://bit.ly/2W6K9Bi

Sponsors:

Dashbot Super Bot Conference 2019: https://sb2019.dashbot.io, 25% group discount code: voicetech
Voice-Connected Home 2019: https://bit.ly/2IZuVwc, 20% discount code: VoiceTech
Dabble Lab: https://youtube.com/dabblelab
Manning books: https://www.manning.com 40% off all books code: podvoicetech19

Find us here:

★ Support this podcast on Patreon ★

Voice Retail - Shilp Agarwal, Blutag Mar 02, 2019

Show notes

Shilp Agarwal is the CEO of Blutag, a voice retail solution that lets customers search/browse a product catalog on Alexa and Google Assistant. We get to hear some product demos showing how customers can quickly reorder products they've bought before, and also browse new options before making an informed choice.

Blutag recently graduated from the Techstars incubator, and are backed by Amazon's Alexa Fund, so we discuss how he got into the programs, and the benefits of the experience.

Shilp has a long history in the retail space, and shares many insights, including how multimodal interfaces, and especially voice enabled TVs, will soon revolutionise online shopping. He reveals the pain points most retailers are trying to solve with voice, Amazon's vision for voice retail, and how the rise of voice search will affect product discoverability.

Links from the show:

Blutag: https://blu.ai
Blutag blog: https://blu.ai/blog
Blutag on Twitter: https://twitter.com/BlutagVoice
Shilp on Twitter: https://twitter.com/ShilpAgarwal_

Sponsors:

Dabble Lab: https://youtube.com/dabblelab

Find us here:

★ Support this podcast on Patreon ★

Nanocasting - Sean Gilligan, Sound Branch Feb 16, 2019

Show notes

Sean Gilligan is the founder of Sound Branch, a team communication app and voice-based social network in which where users create smart voice notes. Sean introduces us to the concept of nanocasting, and explains how it can be used for public broadcasting, team status updates, recruiting new staff, and more.

We discuss the benefits of audio over other mediums, including greater privacy and accountability for content creators, and improved speed and convenience for content consumers.

Sean also explains how audio is unique in providing the perfect combination of authenticity of message and auditability of content, thanks to the combination of speech to text and search technologies. Sound Branch is a feature rich application that could well be the Twitter for voice that so many have been predicting, and this episode will help deepen your understanding of this emerging form of communication.

Highlights from the show:

[22:40] "A massive conversation determines what is right."

Links from the show:

Sound Branch: https://soundbranch.com
Intro on Sound Branch: http://bit.ly/2GSlf3I
Sound Branch Android app: http://bit.ly/2GTAF8f
Sean's interview on the BBC: http://bit.ly/2GTAGcj

Sponsors:

Dabble Lab: https://youtube.com/dabblelab

Find us here:

★ Support this podcast on Patreon ★

Machine Learning Signals - Christopher Oates, audEERING Feb 02, 2019

Show notes

Christopher Oates is a Senior Audio DSP Engineer at audEERING, an audio analysis company that specialises in emotional artificial intelligence. Chris explains how the human voice production system works, and introduces us to a technique called linear predictive coding (LPC) which can extract the features of the voice.

We then focus on machine learning for audio, including using expert audio knowledge along with machine learning methods, leveraging the openSMILE toolkit for feature extraction, and signal processing techniques. Chris explains things really well and even brought along some audio clips to help illustrate the signal concepts.

He then reveals some of the latest projects at audEERING, including using speech analytics in gaming applications, such as whisper detection in a ninja game! It's an awesome episode that is jam-packed with useful and interesting information. Enjoy!

Links from the show:

audEERING: https://www.audeering.com/
Chris on compressed audio and ML: http://bit.ly/2MMW7fX
Blog on emotional games: http://bit.ly/2MOi0LY
Blog on emotion detection: http://bit.ly/2MN0wzj
openSMILE: http://bit.ly/2MRgfO8
Video on Intelligent Machines: http://bit.ly/2MNuraK
CSO interview: http://bit.ly/2MOq8M8

Sponsors:

Dabble Lab: https://youtube.com/dabblelab

Find us here:

★ Support this podcast on Patreon ★

Elevated Voice Design - Vasili Shynkarenka, Invocable Jan 20, 2019

Show notes

Vasili Shynkarenka is CEO and co-founder of Invocable, an online tool that lets you prototype voice applications without coding. Formerly known as Storyline, the company has now pivoted from an Alexa skill builder into a first-class voice application design tool. In our conversation, you'll learn all about the reasons behind the pivot, the main differences between Invocable and Storyline, and how you can use Invocable to design better voice apps.

Vasili shares his experience of seeing thousands of voice applications developed on Storyline, and his advice to voice interaction designers for what works and what doesn't. We discuss the power of multi-modal interaction, and how to design visual interfaces in Invocable. We also discuss predictions for 2019, the major problems with in the voice industry right now, copy cat startups and much more.

Links from the show:

Invocable: https://www.invocable.com
Invocable on Facebook: http://bit.ly/2Mn0gXv
Vasili's email: vasili@invocable.com

Find us here:

★ Support this podcast on Patreon ★

Prototypes & Personas - Kasia Ryniak & Rafal Cymerys, Upside Jan 06, 2019

Show notes

Kasia Ryniak & Rafal Cymerys are the co-founders of Upside, a voice app development agency based in Krakow, Poland, that offer voice interaction design, voice strategy and voice app development. In this episode, you will learn how experienced voice app developers create innovative prototypes, improve voice app engagement, and sell products and services via voice.

First, we explore the creation of prototype of an Alexa skill for StarCraft II, which lets players use voice commands to trigger complex actions. We cover the importance of imbuing your voice assistant with a persona, how voice and visuals fit together to create multi-modal experiences, and a quick walkthrough of building the Alexa skill using the Alexa Skills Kit.

Then Kasia and Rafal introduce us to voicecommerce.js, Upside's new open-source voice framework for integrating an eCommerce storefront with voice-enabled assistants such as Alexa and Google Assistant. We cover the benefits of voice commerce to the consumers, Progressive Web Apps (PWA), and a case study for the fashion industry.

It was a really fun conversation with Kasia and Rafal, and our conversation is packed full of interesting ideas and practical advice. You'll definitely want to listen to it all the way through, and keep a notebook handy!

Links from the show:

Upside homepage: https://upsidelab.io
Upside on Twitter: @UpsideLab
Upside Voice Tech News: @CreateForVoice
Upside on Github: https://github.com/upsidelab/voicecommerce
Starcraft skill design: http://bit.ly/2sdxkYW
Starcraft skill dev: http://bit.ly/2sbEVqL
Voicecommerce.js: http://bit.ly/2sfbNil
Vue Storefront: https://www.vuestorefront.io
PWAs: http://bit.ly/2seMey9

Find us here:

★ Support this podcast on Patreon ★

Conversation Analysis - E. Stokoe, L’boro, S. Albert, Tufts Dec 23, 2018

Show notes

Elizabeth Stokoe is Professor of Social Interaction at Loughborough Uni in the UK, and Saul Albert is a Postdoctoral Research Associate at Tufts University in Massachusetts, United States. Their latest research shows us how to influence the outcomes of conversational interactions, and we discuss the implications of this for voice technology.

We cover what conversation analysis is, with examples from different conversation settings such as first dates, crisis negotiation, and sales calls. Then we discuss the use of nudging to encourage action, and the ethical implications of persuasive voice interfaces. We also arrive at a shocking discovery that today's conversational interfaces are, in fact, not conversational at all!

This is a thought provoking episode that explores the fundamental mechanisms of conversation that we as technologists are trying to emulate. it's especially useful for anyone involved in designing or promoting conversational interfaces, and will make you think about conversation in a whole new way. Subscribe to the podcast and listen now!

Links from the show:

Talk: The Science of Conversation: https://amzn.to/2LxqFlb
The best books on CA: https://voicetechpodcast.com/books
Elizabeth's homepage: http://www.carmtraining.org/
Saul's homepage: http://saulalbert.net/
Elizabeth on Twitter: @LizStokoe
Saul on Twitter: @saul
CA Twitter hashtag: #emca
Conversational Rollercoaster: http://bit.ly/2LwXqPv

Find us here:

★ Support this podcast on Patreon ★

Our TOPPODCAST Picks

Follow Us

Stay Connected

Related Podcasts

Links

Stay Connected