MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset
This addresses the challenge of degraded lip-sync accuracy in 3D talking head generation for non-native languages, which is incremental as it builds on existing methods with new data and a tailored approach.
The paper tackles the problem of generating accurate 3D talking heads from speech in multiple languages by collecting a new multilingual video dataset of over 420 hours in 20 languages and proposing a model with language-specific embeddings, resulting in significantly enhanced multilingual performance.
Recent studies in speech-driven 3D talking head generation have achieved convincing results in verbal articulations. However, generating accurate lip-syncs degrades when applied to input speech in other languages, possibly due to the lack of datasets covering a broad spectrum of facial movements across languages. In this work, we introduce a novel task to generate 3D talking heads from speeches of diverse languages. We collect a new multilingual 2D video dataset comprising over 420 hours of talking videos in 20 languages. With our proposed dataset, we present a multilingually enhanced model that incorporates language-specific style embeddings, enabling it to capture the unique mouth movements associated with each language. Additionally, we present a metric for assessing lip-sync accuracy in multilingual settings. We demonstrate that training a 3D talking head model with our proposed dataset significantly enhances its multilingual performance. Codes and datasets are available at https://multi-talk.github.io/.