Litcius/Paper detail

Text2video: Text-Driven Talking-Head Video Synthesis with Personalized Phoneme - Pose Dictionary

Sibo Zhang, Jiahong Yuan, Miao Liao, Liangjun Zhang

2022ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)32 citationsDOI

Abstract

With the advance of deep learning technology, automatic video generation from audio or text has become an emerging and promising research topic. In this paper, we present a novel approach to synthesize video from the text. The method builds a phoneme-pose dictionary and trains a generative adversarial network (GAN) to generate video from interpolated phoneme poses. Compared to audio-driven video generation algorithms, our approach has a number of advantages: 1) It only needs about 1 min of the training data, which is significantly less than audio-driven approaches; 2) It is more flexible and not subject to vulnerability due to speaker variation; 3) It significantly reduces the preprocessing and training time from several days for audio-based methods to 4 hours, which is 10 times faster. We perform extensive experiments to compare the proposed method with state-of-the-art talking face generation methods on a benchmark dataset and datasets of our own. The results demonstrate the effectiveness and superiority of our approach.

Topics & Concepts

Computer scienceSpeech recognitionPreprocessorBenchmark (surveying)Artificial intelligenceDeep learningAudio analyzerAudio signal processingMultimediaSpeech codingAudio signalGeodesyGeographyGenerative Adversarial Networks and Image SynthesisSpeech and Audio ProcessingMusic and Audio Processing
Text2video: Text-Driven Talking-Head Video Synthesis with Personalized Phoneme - Pose Dictionary | Litcius