YoVDO

AI Generated Voices: Towards Emotive Speech Synthesis

Offered By: ADC - Audio Developer Conference via YouTube

Tags

Speech Synthesis Courses Artificial Intelligence Courses Machine Learning Courses Deep Learning Courses Neural Networks Courses Audio Processing Courses Text to Speech Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the evolution of AI-generated voices and the latest advancements in emotive speech synthesis in this 27-minute conference talk from ADCx India 2024. Delve into the transition from robotic-sounding machine-generated voices to more human-like and engaging AI voices. Discover how deep learning approaches are being used to create synthetic voices capable of expressing emotions such as laughter, sadness, and even crying. Learn about techniques for manipulating Mel Spectrograms to enhance speech expressiveness without relying on large datasets. Gain insights into the future of AI-generated voices and their potential applications in various industries.

Syllabus

AI Generated Voices: Towards Emotive Speech Synthesis - Vibhor Saran - ADCx India 2024


Taught by

ADC - Audio Developer Conference

Related Courses

Introduction to Artificial Intelligence
Stanford University via Udacity Probabilistic Graphical Models 1: Representation
Stanford University via Coursera Artificial Intelligence for Robotics
Stanford University via Udacity Computer Vision: The Fundamentals
University of California, Berkeley via Coursera Learning from Data (Introductory Machine Learning course)
California Institute of Technology via Independent