fresh bytes
Subscribe Now

Artificially intelligent speech generator can fake anyone’s voice

In an effort to inject some life in the automated voices that come out of our apps, AI startup Lyrebird has developed a voice-imitation algorithm that can mimic any person’s voice, and read any text with a predefined emotion or intonation. Incredibly, it can do this after analyzing just a few dozen seconds of pre-recorded audio. In an effort to promote its new tool, Lyrebird produced several audio samples using the voices of Barack Obama, Donald Trump, and Hillary Clinton.

Continue reading (and listening) at Gizmodo

Leave a Reply

featured blogs
Feb 20, 2020
Although I've been exposed to some amazing things in academic and research settings, I can't recall seeing anything this versatile in the public domain....
Feb 19, 2020
AI/ML at DVCon: From Theory to Application  Bringing Hierarchy to DFT Formal Flow for Automotive Safety  Todd Westerhoff on the Value of Solid Design Skills Siemens develops validation program to accelerate AV development AI/ML at DVCon: From Theory to Application M...
Feb 15, 2020
[From the last episode: We looked in more detail at the characteristics of threads.] Last week we ended with a question: we'€™re talking about threads running at the same time, in parallel, but'€¦ if you have only one CPU, how would that even work? That'€™s totally not ...
Feb 13, 2020
J.R. Bonnefoy, Systems Engineer at Samtec, walks us through a live product demonstration of a 70 GHz, high-performance test point system. This demo, from DesignCon 2020, incorporates two new high-performance products.  The demo is based on Samtec'€™s 56 Gbps PAM4 Produ...

Featured Video

Industry’s First USB 3.2 Gen 2x2 Interoperability Demo -- Synopsys & ASMedia

Sponsored by Synopsys

Blazingly fast USB 3.2 Gen 2x2 are ready for your SoC. In this video, you’ll see Synopsys and ASMedia demonstrate the throughput available with Synopsys DesignWare USB 3.2 IP.

Learn more about Synopsys USB 3.2