Voice Tech Podcast

Latest Episodes:

Deaf Person Calling - Benjamin Etienne, Rogervoice Jul 22, 2018

Show notes

Benjamin Etienne is a data scientist at Rogervoice, a mobile app that allows deaf and hard-of-hearing people to use the telephone. Ben shares his inspirational story about how he taught himself data science and machine learning in the evenings, so he could work in a more technical role. He tells us why he's not keen on Kaggle competitions, and why getting a job in data science is the best way to master it.

Ben introduces us to the challenges faced by the deaf and hard-of-hearing community, and how they can overcome them with the help of voice technology. We cover how Rogervoice works from both functional and technical standpoints, and discuss the pros and cons of using a commercial cloud-based speech API versus developing a custom in-house speech-to-text system. Ben reveals his reasoning behind his choice of machine learning models, and describes the advantages of using connectionist temporal classification (CTC).

We then discuss the state of data science today, the limitations of current models and data preprocessing techniques, and how an understanding of the underlying psychology and neurology of users can help us design more effective voice technologies.

Links from this episode:

Rogervoice: https://www.rogervoice.com
CTC intro: https://distill.pub/2017/ctc/
CTC article on Medium: https://gab41.lab41.org/speech-recognition-you-down-with-ctc-8d3b558943f0
...more show notes on the Website : http://bit.ly/voicetechpodcast

Find us here:

★ Support this podcast on Patreon ★

The Art of Sound in Motion - Greg Beller, IRCAM Jul 08, 2018

Show notes

Greg Beller is the Head of the Interfaces Research and Creation team the leading audio research laboratory IRCAM in France. He is also the founder of SYNEKINE, a live entertainment company which mixes art and science in the spirit of research.

We explore the relationship between sound and physical space, and the link between our voices and our gestures. Greg explains what prosody is and its importance in speech and communication. He then demonstrates a number of technological art installations that can modulate the prosody of our speech to augment our capabilities. In the future, this technology will help us to build greater rapport and emotional connection with other humans and voice assistants.

Greg is a fascinating guest, who shows us how explorations into new forms of artistic expression can lead to new technologies for use in our daily lives.

Links from the show:

Greg's website: http://www.gregbeller.com
Synekine website: https://synekine.com/
Greg on Twitter: https://twitter.com/greg_beller
Greg's TedX talk: https://youtu.be/5BQJIFaRDsg
Elliptic Labs: http://www.ellipticlabs.com/
Eyesight Tech: http://www.eyesight-tech.com/
Neatebox / Welcome app: https://www.neatebox.com/

Find us here:

★ Support this podcast on Patreon ★

Building Knight Rider's KITT - Charles Cadbury, Champers Advisory Jun 15, 2018

Show notes

In this episode I talk with Charles Cadbury, owner of the London-based technology consultancy, Champers Advisory, about his experience building voice applications, and the fascinating future of voice technology. He was great fun to talk to, and had plenty of surprising facts and interesting stories to share. You're going to really enjoy listening to this episode!

Charles has built or consulted on over 350 digital products for his clients over the years, covering web, social, mobile, and and now Voice. He has most recently worked with Lola.tech, helping them to create Dazzle.ai, a product that enables personalised digital conversations between travel customers and travel providers across voice and text channels.

Charles shares his extensive knowledge and experience on a wide range of topics related to voice. We cover the challenges when working with client data, how payment transactions can and will be handled over voice, and how voice assistants will change the landscape of consumer sales and marketing, and much more.

Links from the show:

Champers Advisory Consultancy https://champersadvisory.com
Charles Cadbury Personal Site https://charlescadbury.com
Charles Cadbury on Twitter https://twitter.com/CharlesCadbury
Dazzle.ai Voice Platform https://www.dazzle.ai/
Lola.tech https://www.lola.tech/

Find us here:

★ Support this podcast on Patreon ★

Vivatech 2018 Voice Startup Summary May 27, 2018

Show notes

This episode covers 8 of the most interesting voice startups that I found at the Vivatech technology conference in Paris, France.

Included in this episode is a voice transcription and synthesis mobile app for the hard of hearing, a voice enabled smart alarm clock that can monitor your sleep quality, a robot behaviour system that delivers CMS content in person, and a comprehensive voice assistant platform that can handle multiple requests in a single query.

Links from the show:

Rogervoice mobile app: http://rogervoice.com
Ideta voice assistant platform: http://meet-ideta.com/
Holi / Bonjour alarm clock: http://holi.io/
Askhub analytics: https://www.askhub.io/
Acapela group speech synthesis: http://www.acapela-group.com/
Humanizing technologies: http://humanizing.com/
Cochlear.ai acoustic event detection: http://cochlear.ai
Soundhound Houndify voice assistant platform: https://www.houndify.com/

Find us here:

★ Support this podcast on Patreon ★

Voice AI for eCommerce - John Fitzpatrick, Voysis May 19, 2018

Show notes

John Fitzpatrick is the VP of Product & Engineering at Voysis, a leading voice technology company that builds custom Voice AI solutions for businesses. They are currently focused on the ecommerce vertical, helping to voice-enable mobile apps and websites to augment the shopping experience.

In our conversation we cover a range of topics including the major components of the Voysis system, the technologies and tools John's team used to build it, and the challenges they faced. We also discuss how Voysis protects a user's privacy and the implications of the GDPR regulation that comes into force soon.

It was a pleasure to talk with John and learn from such an experienced engineer. Whether you're currently building voice AI systems or are just interested in learning about how they work, this episode will have plenty for you.

Links from the show:

Voysis: https://voysis.com/
EESEN project: https://github.com/srvk/eesen
Kaldi toolkit: http://kaldi-asr.org/doc/about.html
Open FST library: http://openfst.org/twiki/bin/view/FST/WebHome
Spacy NLP toolkit: https://spacy.io/
Kubernetes containerized application management: https://kubernetes.io/
Luigi batch process automation: https://github.com/spotify/luigi
Oxford Deep NLP course (from deepmind team): https://www.cs.ox.ac.uk/teaching/courses/2016-2017/dl/

Find us here:

★ Support this podcast on Patreon ★

Speech to Text - Eric Bolo, Batvoice Apr 29, 2018

Show notes

Eric Bolo is the CTO of Batvoice Technologies, a speech analytics startup based in Paris, France. Eric talks about building a custom speech-to-text system for their flagship product, Call Watch.

He introduces us to speech analytics and audio-mining, and describes some typical applications. We go into detail about speech-to-text (STT) technologies, and discuss the pros and cons of using cloud STT services such as Google speech versus building a custom STT system yourself.

Eric tells us about the latest open source tools and frameworks for building STT systems, and how to get that precious voice data to train our models. We learn how to build and annotate a custom voice dataset ourselves, and hear his advice on starting a voice first company.

This is a great first episode to kick off the series! Eric is super smart, with excellent technical skills and a real passion for voice technology. We already know each other quite well, so I couldn't think of anyone I'd rather have as my first guest on the show. I know you're gonna enjoy hearing what he had to say!

Links from the show: