The Feed The Official Libsyn Podcast cover image

235 Nudging For Podcast Feedback

The Feed The Official Libsyn Podcast

CHAPTER

Microsoft AI Models to Detect Speech Synthesized by Valley

Valley could synthesize speech that maintains speaker identity it may carry potential risks in misuse of the model such as spoofing voice identification or impersonating a specific speaker. It is possible to build a detection model to discriminate whether an audio clip was synthesized by Valley. We will also put Microsoft AI principles into practice when further developing the models and quote sky net sky net is using this oh my god great awesome any who I'm just laying it out there because does anybody see any problems with this well you know your descript could learn voice it couldn't learn it from three seconds needed more correct.

00:00
Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner