The Stack Overflow Podcast23 Kesä 2021

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

We chatted with three guests:

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.

Kokeile Premiumia

Nauti 14 päivää ilmaiseksi

Tilaa Premium

Jaksot(903)

“Are AI agents ready for the enterprise?”

Deepak works on Amazon Q Developer, a GenAI-powered coding assistant that includes autonomous agents.Thinking, Fast and Slow by psychologist Daniel Kahneman is one of those books that’s a classic for a reason—and it’s more relevant to today’s AI landscape than you might think.Connect with Deepak on LinkedIn. Congrats to Stack Overflow user Morten Zilmer, who earned a Lifeboat badge by explaining Multiplication of two different bit numbers in VHDL.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

28 Maalis 202528min

AI is shifting focus from syntax to critical thinking

They also: Emphasize the critical role of customer feedback in shaping products, highlighting how continuous feedback loops drive innovation and improvement. Explore how AI is empowering non-technical team members and enabling meaningful collaboration between developers and other departments. Discuss the potential of GenAI as a learning tool and the importance of prompt engineering as a key skill for future developers. Episode notes: Connect with Lee Faus on LinkedIn, X, and learn more about GitLab. Learn more about creating a private instance of Stack Overflow for your team or org with Stack Overflow for Teams. Read about Knowledge Solutions, a subscription-based API service that provides continuous access to Stack Overflow’s public dataset to train and fine-tune large language models. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

27 Maalis 202536min

“The power of the humble embedding”

Pinecone is a purpose-built vector database. Get started with their docs here.Connect with Edo on LinkedIn. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

25 Maalis 202529min

An AI future free of slop

Read more about Stack Overflow’s future here.Learn more about HumanX here. Missed it this year? The event takes place again on April 7-9, 2026 in San Francisco. Early birds can register here.Follow Prashanth on LinkedIn or explore his posts on our blog.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

21 Maalis 202522min

WBIT #5: Building a framework to lure web devs to mobile

Ionic is a platform for building and deploying modern mobile applications and micro frontend experiences. It’s open source, too. Two mobile tools got multiple mentions on this episode: Xcode and Material Design. Connect with Maria on LinkedIn. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

19 Maalis 202540min

Improving error monitoring with AI

Sentry is an application monitoring software. Explore the Sentry docs or get started in the sandbox.Connect with Tillman on LinkedIn. You can also read his posts on the Sentry blog.Listeners, how do you handle stack traces? How do you trace the root cause? Let us know at podcast@stackoverflow.com. Sentry user? The company would love to hear your feedback. Let them know what you think on Discord. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

18 Maalis 202527min

Can climate tech startups address the current crisis?

Lisbeth cofounded and coleads the Compute for Climate Fellowship, which funds climate tech startups using advanced cloud computing and AI. Applications are open until April 6, 2025.Read about how some climate tech startups are leveraging GenAI.Connect with Lisbeth on LinkedIn. Stack Overflow user JohnsonYuan earned a Lifeboat badge by answering Why can't I enter the url on my phone's browser to view my live site?. Nice work!See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

14 Maalis 202525min

Junky data is like an out-of-tune guitar—it prevents AI harmony

Welcome to Leaders of Code, a new business segment of the Stack Overflow podcast. On this show, we chat with business, tech, and engineering leaders from forward-thinking companies across industries about their business strategies, the challenges and opportunities of building high-performing teams, driving innovation, leveraging the power of AI, and other key topics. Tune in every second Thursday for real-world success stories, actionable strategies, and fresh perspectives to help you navigate your leadership and growth journey.In our very first episode, Stack Overflow CEO Prashanth Chandrasekar talks to Don Woodlock, Head of Global Healthcare Solutions at InterSystems, about the challenges in their AI journey and the critical role of a robust data strategy in any successful AI initiative.They also: Discuss the importance of maintaining a human-centric approach when automating processes with GenAI, emphasizing trust-building as a top priority. Dive deep into specific use cases and real-world successes and obstacles in AI implementation, from data scalability to system integration. Share their perspectives on common misconceptions about AI in today’s landscape. Episode notes: Connect with Don Woodlock on LinkedIn, explore his video series Code to Care, and learn more about InterSystems. Read more about Knowledge-as-a-service. Learn more about creating a private instance of Stack Overflow for your team or org with, Stack Overflow for Teams. Read more about OverflowAPI, a subscription-based API service that provides continuous access to Stack Overflow’s public dataset to train and fine-tune large language models. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

13 Maalis 202540min

Kaikki yhdessä sovelluksessa

Kuuntele kaikki suosikkipodcastisi ja -äänikirjasi yhdessä paikassa.

Sinulle valikoitua sisältöä

Podme-sovelluksessa kokoat suosikkisi helposti omaan kirjastoosi. Saat meiltä myös kuuntelusuosituksia!

Jatka kuuntelua koska tahansa

Voit jatkaa siitä mihin jäit, myös offline-tilassa.

Premium

9,99 €/kk

Kaikki premium-podcastit
Ei mainoksia
Ei sitoutumista, peruuta koska tahansa

Aloita 14 päivän kokeilu

Premium

13,99 €/kk

Kaikki premium-podcastit
Ei mainoksia
Ei sitoutumista, peruuta koska tahansa
Yksi lisäkäyttäjä

Kokeile 14 päivää maksutta

Suosittua kategoriassa Liike-elämä ja talous

Tarinat ja äänet, joita rakastat kuunnella

Kuuntele kaikki suosikkipodcastisi ja -äänikirjasi

Lue lisää