Towards a low bandwidth talking face using appearance models
نویسندگان
چکیده
The paper is motivated by the need to develop low bandwidth virtual humans capable of delivering audio-visual speech and sign language at a quality comparable to high bandwidth video. The number of bits required for animating a virtual human is significantly reduced by using an appearance model combined with parameter compression. A new perceptual method is introduced and used to evaluate the quality of the synthesised sequences. It appears that 3.6 kbits.s can still yield acceptable quality.
منابع مشابه
Near-videorealistic synthetic visual speech using non-rigid appearance models
In this paper we present work towards videorealistic synthetic visual speech using non-rigid appearance models. These models are used to track a talking face enunciating a set of training sentences. The resultant parameter trajectories are used in a concatenative synthesis scheme, where samples of original data are extracted from a corpus and concatenated to form new unseen sequences. Here we e...
متن کاملTalking faces for MPEG-4 compliant scalable face-to-face telecommunication
We present here a system that captures, encodes and renders speaker-specific speech gestures in a MPEG-4 compliant framework. The process is eased by two original options: (a) the use of a specific video capture via a head-mounted camera, (b).the a priori construction of speaker-specific shape and appearance models. We will show that speaker-specific articulatory movements can be straightforwar...
متن کاملTowards Generic Fitting using Discriminative Active Appearance Models Embedded on a Riemannian Manifold
A solution for Discriminative Active Appearance Models is proposed. The model consists in a set of descriptors which are covariances of multiple features evaluated over the neighborhood of the landmarks whose locations are governed by a Point Distribution Model (PDM). The covariance matrices are a special set of tensors that lie on a Riemannian manifold, which make it possible to measure the di...
متن کاملEvaluation of a talking head based on appearance models
In this paper we describe how 2D appearance models can be applied to the problem of creating a near-videorealistic talking head. A speech corpus of a talker uttering a set of phonetically balanced training sentences is analysed using a generative model of the human face. Segments of original parameter trajectories corresponding to the synthesis unit are extracted from a codebook, normalised, bl...
متن کاملA Cantonese Speech-Driven Talking Face Using Translingual Audio-to-Visual Conversion
This paper proposes a novel approach towards a videorealistic, speech-driven talking face for Cantonese. We present a technique that realizes a talking face for a target language (Cantonese) using only audio-visual facial recordings for a base language (English). Given a Cantonese speech input, we first use a Cantonese speech recognizer to generate a Cantonese syllable transcription. Then we ma...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Image Vision Comput.
دوره 21 شماره
صفحات -
تاریخ انتشار 2001