AutoLV: Automatic Lecture Video Generator

TL;DR

AutoLV is an end-to-end system that automatically generates realistic lecture videos from slides, voice, and portrait, reducing instructor workload and enabling multilingual dissemination.

Contribution

It introduces a novel integrated system combining speech synthesis with speaker adaptation and talking-head generation for lecture videos.

Findings

Outperforms existing methods in authenticity and naturalness

Capable of multilingual and accent variations

Reduces instructor workload significantly

Abstract

We propose an end-to-end lecture video generation system that can generate realistic and complete lecture videos directly from annotated slides, instructor's reference voice and instructor's reference portrait video. Our system is primarily composed of a speech synthesis module with few-shot speaker adaptation and an adversarial learning-based talking-head generation module. It is capable of not only reducing instructors' workload but also changing the language and accent which can help the students follow the lecture more easily and enable a wider dissemination of lecture contents. Our experimental results show that the proposed model outperforms other current approaches in terms of authenticity, naturalness and accuracy. Here is a video demonstration of how our system works, and the outcomes of the evaluation and comparison: https://youtu.be/cY6TYkI0cog.