Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications Article Swipe

MAKE IMPACT

Karren Yang , Anurag Ranjan , Jen-Hao Rick Chang , Raviteja Vemulapalli , Oncel Tuzel · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2311.18168

We consider the task of animating 3D facial geometry from speech signal. Existing works are primarily deterministic, focusing on learning a one-to-one mapping from speech signal to 3D face meshes on small datasets with limited speakers. While these models can achieve high-quality lip articulation for speakers in the training set, they are unable to capture the full and diverse distribution of 3D facial motions that accompany speech in the real world. Importantly, the relationship between speech and facial motion is one-to-many, containing both inter-speaker and intra-speaker variations and necessitating a probabilistic approach. In this paper, we identify and address key challenges that have so far limited the development of probabilistic models: lack of datasets and metrics that are suitable for training and evaluating them, as well as the difficulty of designing a model that generates diverse results while remaining faithful to a strong conditioning signal as speech. We first propose large-scale benchmark datasets and metrics suitable for probabilistic modeling. Then, we demonstrate a probabilistic model that achieves both diversity and fidelity to speech, outperforming other methods across the proposed benchmarks. Finally, we showcase useful applications of probabilistic models trained on these large-scale datasets: we can generate diverse speech-driven 3D facial motion that matches unseen speaker styles extracted from reference clips; and our synthetic meshes can be used to improve the performance of downstream audio-visual models.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2311.18168

PDF

https://arxiv.org/pdf/2311.18168

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4389260901

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4389260901

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2311.18168

Digital Object Identifier

Title

Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-11-30

Full publication date if available

Authors

Karren Yang, Anurag Ranjan, Jen-Hao Rick Chang, Raviteja Vemulapalli, Oncel Tuzel

List of authors in order

Landing page

https://arxiv.org/abs/2311.18168

Publisher landing page

PDF URL

https://arxiv.org/pdf/2311.18168

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2311.18168

Direct OA link when available

Concepts

Computer science, Probabilistic logic, Benchmark (surveying), Speech recognition, Task (project management), Artificial intelligence, Statistical model, Motion (physics), Set (abstract data type), Fidelity, Polygon mesh, Face (sociological concept), SIGNAL (programming language), Machine learning, Geodesy, Sociology, Management, Social science, Computer graphics (images), Economics, Programming language, Geography, Telecommunications

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2025: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload