From search trees to neural nets, a deep dive into natural language processing
The Stack Overflow Podcast23 Kesä 2021

From search trees to neural nets, a deep dive into natural language processing

We chatted with three guests:

Miguel Jetté: Head of AI R&D

Josh Dong: AI Engineering Manager

Jenny Drexler: Senior Speech Scientist

When Jette was studying mathematics in the early 2000s, his focus was on computational biology, and more specifically, phylogenetic trees, and DNA sequences. He wanted to understand the evolution of certain traits and the forces that explain why our bones are a certain length or our brains a certain size. As it turned out, the algorithms and techniques he learned in this field mapped very well to the emerging discipline of automatic speech recognition, or ASR.

During this period, Montreal was emerging as a hotbed for artificial intelligence, and Jette found himself working for Nuance, the company behind the original implementation of Siri. That experience led him to several positions in the world of speech recognition, and he eventually landed at Rev, where he founded the company’s AI department.

Jette describes Rev as an “Uber for Transcription.” Anyone can sign up for the platform and earn money by listening to audio submitted by clients and transcribing the speech into text. This means the company has a tremendous dataset of raw audio that has been annotated by human beings and, in many cases, assessed a second time by the client. For someone looking to build an AI system that mastered the domain of speech to text, this was a goldmine.

Jette built the earliest version of Rev’s AI, but it was up to our second guest, Josh Dong, to productize and scale that system. He helped the department transition from older technologies like Perl to more popular languages like Python. He also focused on practical concerns like modularity and reusable components. To combine machine learning and DevOps, Dong added Docker containers and a testing pipeline. If you’re interested in the nuts and bolts of keeping a system like Rev’s running at tremendous scale, you’ll want to check out this part of the show.

We also explore some of the fascinating future and promise this technology holds in our time with Jenny Drexler. She explains how Rev is moving from a hybrid model—one that combines Jette’s older statistical techniques with Dong’s newer machine learning approach—to a new system that will be ML from end-to-end. This will open up the door for powerful applications, like a single system that can convert speech text across multiple languages in a single piece of audio.

“One of the things that's really cool about these end to end models is that basically, whatever data you have, it can learn to handle it. So a very similar architecture can do sequence to sequence learning with different kinds of sequences. The model architecture that you might use for speech recognition can actually look very similar to what you might use for translation. And you can use that same architecture, to say, feed in audio in lots of different languages and be able to do transcription for any of them within one model. It's much harder with the hybrid models to sort of put all the right pieces together to make that happen,” explains Drexler.

If you’re interested in learning more about the past, present, and future of artificial intelligence that can understand our spoken language and learn how to respond, check out the full episode. If you want to learn more about Rev or check out some of the positions they have open, you can find their careers page here.

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Jaksot(903)

Sharing the power of the command line

Sharing the power of the command line

Warp is an intelligent terminal that combines AI tools and developer resources in one interface. Zach’s hope was to give more developers access to the arcane magic of the command line.Connect with Zach on LinkedIn.If you’re a terminal user, which one is your go-to and why? Let us know at podcast@stackoverflow.com. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

11 Maalis 202524min

Is Postgres the best database for GenAI?

Is Postgres the best database for GenAI?

Postgres is an open-source database. EDB offers enterprise-grade features and support for Postgres from self-managed to fully-managed, cloud-based DBaaS.Find Jezz on LinkedIn. Shoutout to Stack Overflow user Jonny, who won a Populist badge with their exceptional answer to quantile function for a vector of dates.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

7 Maalis 202528min

How can AI perform on the edge?

How can AI perform on the edge?

Episode notes:Infineon is a global semiconductor company for power systems and IoT.You can connect with Clark and Alexander on LinkedIn. Congrats to Lifeboat badge winner hdsenevi for their answer on Unrecognized font family 'Roboto' - React Native iOS.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

5 Maalis 202527min

Secure coding beyond just memory safety

Secure coding beyond just memory safety

Semgrep is an AppSec platform that lets devs deploy static application security testing (SAST), software composition analysis (SCA), and secret scans. Explore their docs.Tanya is the author of Alice and Bob Learn Secure Coding and Alice and Bob Learn Application Security.She’s also written for our blog:Three layers to secure a software development organization and Continuous delivery, meet continuous security.Secure coding might be an issue of national security. Follow Tanya on LinkedIn or check out her website.Stack Overflow user Reishin earned a Populist badge with their answer to piping from stdin to a python code in a bash script.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

4 Maalis 202534min

“Translation is the tip of the iceberg”: A deep dive into specialty models

“Translation is the tip of the iceberg”: A deep dive into specialty models

Smartling is an enterprise translation platform that includes AI-powered translation solutions.Connect with Olga on LinkedIn. Kudos to Stack Overflow user Suleka_28, who earned a Populist badge by explaining how to convert logits to probability in binary classification in tensorflow.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

28 Helmi 202531min

Writing tests with AI, but not LLMs

Writing tests with AI, but not LLMs

Diffblue Cover is an AI agent for testing complex Java code at scale. Check out their docs to get started automating unit tests today.This article will help you understand the difference between Diffblue Cover and Copilot.Find Animesh on LinkedIn.Stack Overflow user Keet Sugathadasa earned a Populist badge by answering a question in the CI/CD Collective: Gitlab CI CD variable are not getting injected while running gitlab pipeline.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

25 Helmi 202541min

One quality every engineering manager should have? Empathy.

One quality every engineering manager should have? Empathy.

CLEAR is an identity company trying to take the friction out of air travel (such as with TSA PreCheck, available through CLEAR), stadium events, and other experiences that require security screening. Find Caitlin on LinkedIn. Shoutout to Stack Overflow user Patrick Pijnappel, who earned a Populist badge with their answer to Redirect all output to file using Bash on Linux?. It’s helped 230,000 people and counting.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

21 Helmi 202535min

WBIT #4: Using GIS to understand the rivers and the lakes that you’re used to

WBIT #4: Using GIS to understand the rivers and the lakes that you’re used to

Forerunner provides a platform for floodplain management. Do you also have gnarly caching issues? Check out an overview of how we use caching at Stack Overflow. If you want to connect with Lauren, head over to her LinkedIn page. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

19 Helmi 202532min

Suosittua kategoriassa Liike-elämä ja talous

sijotuskasti
mimmit-sijoittaa
psykopodiaa-podcast
rss-rahapodi
ostan-asuntoja-podcast
rss-lahtijat
oppimisen-psykologia
pomojen-suusta
taloudellinen-mielenrauha
rahapuhetta
kasvun-kipuja
sijoituspodi
rss-seuraava-potilas
rss-viisas-raha-podi
rss-neuvottelija-sami-miettinen
rss-rahamania
rss-h-asselmoilanen
rss-laakispodi
rss-farmapodi
rss-rikasta-elamaa