Скачать или смотреть Chris Buchanan (CereProc) - Performance Synthesis using CereWave

Chris Buchanan (Audio Development Engineer at CereProc) - “Performance Synthesis using CereWave”

Abstract
In the last two years speech synthesis technology has changed beyond recognition. Being able to create seamless copies of voices is a reality, and the manipulation of voice quality using synthesis techniques can now produce dynamic audio content that is impossible to differentiate from natural spoken output.

Speech synthesis is also speech editing software. It will allow us to create artificial spoken and sung performances better than many human singers, graft expressive techniques
from one singer to another, and using analysis-by-synthesis categorise and evaluate.

In this talk we approach this expanding field in a modern context and give some examples, introduce CereWave and its deep neural net speech waveform generation engine, introduce our vocal puppetry and voice morphing applications, and discuss the future trajectory of this powerful technology from Text-to-Speech to music and audio engineering platforms.

--
Join the Audio Programmer Community: https://theaudioprogrammer.com/commun...

Submit a talk, demo, or proposal:
https://theaudioprogrammer.com/submit...

Support the channel:   / theaudioprogrammer  

Website: https://www.theaudioprogrammer.com
Instagram:   / theaudioprogrammer  
Facebook:   / theaudioprogrammer  
Twitter:   / audioprogrammer