Speech driven lip synthesis using viseme based hidden markov models

US6366885B1 · kind B1 · utility

Assignee

• International Business Machines Corporation · US

Inventors

• Sankar Basu · Tenafly, US
• Tanveer Atzal Faruquie · New Delhi, IN
• Chalapathy Neti · Yorktown Heights, US
• Nitendra Rajput · New Delhi, IN
• Andrew W. Senior · New York, US
• L. Venkata Subramaniam · New Delhi, IN
• Ashish Verma · New Delhi, IN

Key dates

• Filing date: Aug 27, 1999
• Grant date: Apr 2, 2002
• Expiry date: Aug 27, 2019

Classification

• Technology area (CPC G): Physics
• CPC primary: G10L2021/105
• WIPO field: Audio-visual technology
• WIPO sector: Electrical engineering

Abstract

A method of speech driven lip synthesis which applies viseme based training models to units of visual speech. The audio data is grouped into a smaller number of visually distinct visemes rather than the larger number of phonemes. These visemes then form the basis for a Hidden Markov Model (HMM) state sequence or the output nodes of a neural network. During the training phase, audio and visual features are extracted from input speech, which is then aligned according to the apparent viseme sequence with the corresponding audio features being used to calculate the HMM state output probabilities or the output of the neutral network. During the synthesis phase, the acoustic input is aligned with the most likely viseme HMM sequence (in the case of an HMM based model) or with the nodes of the network (in the case of a neural network based system), which is then used for animation.