Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Deep learning speech synthesis
open-in-new
<p>Deep learning speech synthesis refers to the application of <a href="/facts/Deep_learning/JLuwD3ea">deep learning</a> models to generate natural-sounding human speech from written text (text-to-speech) or spectrum (<a href="/facts/Vocoder/sSymnRBU">vocoder</a>). Deep <a href="/facts/Neural_network_(machine_learning)/6V1jMlkx">neural networks</a> are trained using large amounts of recorded speech and, in the case of a text-to-speech system, the associated labels and/or input text. </p>