The Unreasonable Effectiveness of Speech Data
About this episode
Piotr Żelasko is Head of Research at Meaning, a startup building an AI platform using speech technologies. He has years of experience in speech technologies, both as a researcher and as a software engineer. We recorded this episode on the week of the release of Whisper, deep learning model (from OpenAI) that approaches human level robustness and accuracy on English speech recognition. Our conversation centered on Whisper and speech recognition, but also touched on the new speech data processing tools (Lhotse, k2, Icefall) that we described in our recent post.
Download a FREE copy of our recent 2022 Trends Report (Data, Machine Learning, AI): https://gradientflow.com/2022trendsreport/
Subscribe: Apple • Android • Spotify • Stitcher • Google • AntennaPod • RSS.
Detailed show notes can be found on The Data Exchange web site.
Get every episode summarized
Each time The Data Exchange with Ben Lorica publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from The Data Exchange with Ben Lorica
Your AI Agent Is Costing You More Than You Think
The Data Exchange with Ben Lorica
Reasoning Doesn't Start With Language
The Data Exchange with Ben Lorica
An Agent Is Just an LLM in a For-Loop
The Data Exchange with Ben Lorica
The Bloomberg Terminal for AI Compute
The Data Exchange with Ben Lorica