Deaf Person Calling — Benjamin Etienne, Rogervoice — Voice Tech Podcast ep.006
Full episode:
https://voicetechpodcast.com/episodes/006-deaf-person-calling-benjamin-etienne-rogervoice-voice-tech-podcast/
Episode description:
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 the show:
- CTC intro: https://distill.pub/2017/ctc/
- CTC article on Medium: https://gab41.lab41.org/speech-recognition-you-down-with-ctc-8d3b558943f0
- CTC dissertation by A.Graves: https://www.cs.toronto.edu/~graves/phd.pdf
- Memory networks — one-shot-learning: https://arxiv.org/abs/1605.06065
- Neural Turing Machines: https://arxiv.org/abs/1410.5401
“An Amplitude Modulation Model for Speech Perception” https://pdfs.semanticscholar.org/28e6/80db1df1f7506d8625012b5f11806c723ea6.pdf - “Brain-inspired speech segmentation”: https://www.nature.com/articles/srep37647.pdf
- Baidu Deepspeech: http://research.baidu.com/
- Mozilla Common Voice Project: https://voice.mozilla.org/en
- TEDlium English speech recognition training corpus from TED talks: http://www.openslr.org/7/
- Voxforge GPL Transcribed Speech corpus: http://www.voxforge.org/
- Librispeech ASR corpus: http://www.openslr.org/12/
- Andrew ING Machine Learning MOOC: https://www.coursera.org/learn/machine-learning
- Geoffrey Hinton MOOC: https://www.coursera.org/learn/neural-networks
- Facebook Pytorch: https://pytorch.org/
- Google Tensorflow: https://www.tensorflow.org/
Subscribe to get future episodes:
- Apple iTunes : https://apple.co/2LqW4ol
- Google Podcasts : http://bit.ly/voicetechpodcast-google
- Google Android : http://bit.ly/voicetechpodcast-android
- Stitcher : http://bit.ly/voicetechpodcast-stitcher
- Spotify : https://spoti.fi/2IZr5hm
- Alexa : https://amzn.to/2mr8mCj
- Newsletter : http://bit.ly/voicetechpodcast-newsletter
- Website : http://bit.ly/voicetechpodcast
How to support the Voice Tech Podcast:
- Tell a friend about us or share on social media!
- Leave a 5 star review on iTunes: https://apple.co/2LqW4ol
- Leave a 5 star review on Stitcher: http://bit.ly/voicetechpodcast-stitcher
- Become a patron at: http://bit.ly/voicetechpodcast-patreon