Recording Clean Voice Datasets While Walking

From My Weird Prompts · 26:59

Show by Daniel Rosehill

Speech recognition datasets easily tolerate digital signal processing, but text-to-speech voice models memorize every limiter, noise gate, and ducked volume level as part of a speaker's actual voice. Recording clean, dual-purpose training data while pacing around means rethinking equipment from scratch. A close look at body-mounted dynamic mics, headworn options like the Shure WH20XLR, and handheld broadcast standards like the Electro-Voice RE50B reveals the acoustic trade-offs between mechanical handling noise, proximity drift, and uncolored room tone. Episode 6722 — myweirdprompts.com/n/6722 (permanent short link: myweirdprompts.com/127895) Listen on Android: MWP FM Player — myweirdprompts.com/apk

More episodes of My Weird Prompts

More episodes

PodSearch is a free, independent podcast search engine. Read about PodSearch, the privacy policy or contact us.