Current state of text to speech with small input data

Channel:
Sweden Daniel Persson
Subscribers:
11,800
Published on ● Video Link: https://www.youtube.com/watch?v=oYpuFbfkM3U


Duration: 10:50
214 views
10

We look at two projects that tries to recreate a voice using extreamly small amount of voice data.

Please follow me on twitter
http://twitter.com/kalaspuffar

Learn more with a Coursera course
https://coursera.pxf.io/DanielPersson

My merchandise:
https://teespring.com/stores/daniel-persson

Outro music: Sanaas Scylla



Other Videos By Daniel Persson


2020-06-14OpenJDK 15 - Unsafe Garbage
2020-06-07How to use Heartbeat and DRBD for HA (high availability)
2020-05-31How to setup a PWA (progressive web app) with Lighthouse CI on GitHub actions
2020-05-24How to setup an on prem function as a service
2020-05-17Autoscaling Kubernetes using RabbitMQ
2020-05-10Building a web component module with hybrids
2020-05-03How to automate a Linux OS installation on Virtualbox
2020-04-26Comparing 3 java build tools (Ant vs Maven vs Gradle)
2020-04-19How to setup up a local copy of jitsi video conferencing
2020-04-12How to use autotools (automake, autoconf, aclocal, autoheader)
2020-04-12Current state of text to speech with small input data
2020-04-05Linux by example - Perl and network utils
2020-03-30How to setup a Focusrite audio interface in Windows
2020-03-2912 Factors for micro service applications
2020-03-29Doing some evening coding
2020-03-22Using JMeter for performance testing
2020-03-20How can we help with Folding@Home for folding proteins
2020-03-16Tips for working at home
2020-03-15Looking at Gitea as a Git host solution
2020-03-08Linux by example - ACL, Psmisc and Sed
2020-03-02Linux by example - GCC, Ncurses, attr and bzip2


Tags:
text2speech
Daniel Persson
how-to
example
explaination
15.ai
fifteen.ai
Real Time Voice Cloning