Iterative Text-Based Editing of Talking-Heads Using Neural Retargeting

نویسندگان

چکیده

We present a text-based tool for editing talking-head video that enables an iterative workflow. On each iteration users can edit the wording of speech, further refine mouth motions if necessary to reduce artifacts, and manipulate non-verbal aspects performance by inserting gestures (e.g., smile) or changing overall style energetic, mumble). Our requires only 2 3 minutes target actor it synthesizes in about 40 seconds, allowing quickly explore many possibilities as they iterate. approach is based on two key ideas. (1) develop fast phoneme search algorithm identify phoneme-level subsequences source repository best match desired edit. This our loop. (2) leverage large new self-supervised neural retargeting technique transferring actor. allows us work with relatively short videos, making applicable real-world scenarios. Finally, our, refinement controls give ability fine-tune synthesized results.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Talking Heads

This paper describes an interactive presentation that introduces the Talking Heads website, which was originally proposed at the AVSP'97 meeting in Rhodes, Greece. Talking Heads is an effort to bring together information from a wide range of sources. The site provides interactive access to multimodal material in both its original form and as summarized by us. In addition, the authors have provi...

متن کامل

Image-based Talking Heads using Radial Basis Functions

In recent years talking heads have received a great deal of interest, both in their application to natural humancomputer dialogue, and their benefit to the intelligibility of synthesised speech. A model for the realistic synthesis of visual speech animation is described in this paper. Images representing the key visual speech poses (visemes) are pre-recorded and labelled. Transitions between vi...

متن کامل

A text-speech synchronization technique with applications to talking heads

In human communication, speech understanding is greatly improvedby the bimodal acoustic-visual effect with respect to simple speech communication, in particular when the communication takes place in noisy environments. In this paper we propose a novel synchronization procedure between text and speech, to reduce the time consumption in the development of friendly audio--visual interfaces or auth...

متن کامل

Retargeting cued speech hand gestures for different talking heads and speakers

Cued Speech is a communication system that complements lip-reading with a small set of possible handshapes placed in different positions near the face. Developing a Cued Speech capable system is a time-consuming and difficult challenge. This paper focuses on how an existing bank of reference Cued Speech gestures, exhibiting natural dynamics for hand articulation and movements, could be reused f...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: ACM Transactions on Graphics

سال: 2021

ISSN: ['0730-0301', '1557-7368']

DOI: https://doi.org/10.1145/3449063