Towartds Robust Lipreading

نویسندگان

  • Wen Gao
  • Jiyong Ma
  • Rui Wang
  • Hongxun Yao
چکیده

In this paper, a robust and fast approach to lip detecting and lip-reading is presented. The approach combines the information of lip color with the geometrical features of lips in human face. This technique makes it possible to derive lip regions in real time under regular illumination conditions. The experimental results with more than 2000 images have shown that the approach to locating lips is very efficient both in locating speed and locating accuracy. Recognition tests were conducted on Chinese phrases. The approach achieved an accuracy of 90% for speaker dependent recognition task.

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

An Image Transform Approach for HMM based Automatic Lipreading

This paper concentrates on the visual front end for hidden Markov model based automatic lipreading. Two approaches for extracting features relevant to lipreading, given image sequences of the speaker's mouth region, are considered: A lip contour based feature approach, which rst obtains estimates of the speaker's lip contours and subsequently extracts features from them, and an image transform ...

متن کامل

Using Surface-Learning to improve Speech Recognition with Lipreading

We explore multimodal recognition by combining visual lipreading with acoustic speech recognition. We show that combining the visual and acoustic clues of speech improves the recog­ nition performance significantly especially in noisy environment. We achieve this with a hybrid speech recognition architecture, consisting of a new visual learning and tracking mechanism, a channel robust acoustic ...

متن کامل

Audio-Visual Based Multi-Sample Fusion to Enhance Correlation Filters Speaker Verification System

In this study, we propose a novel approach for speaker verification system that uses a spectrogram image as features and Unconstrained Minimum Average Correlation Energy (UMACE) filters as classifiers. Since speech signal is a behavioral signal, the speech data has a tendency not to consistently reproduce due to the change of speaking rates, health, emotional conditions, temperature and humidit...

متن کامل

A functional-anatomical model for lipreading.

Regional cerebral blood flow (rCBF) PET scans were used to study the physiological bases of lipreading, a natural skill of extracting language from mouth movements, which contributes to speech perception in everyday life. Viewing connected mouth movements that could not be lexically identified and that evoke perception of isolated speech sounds (nonlexical lipreading) was associated with bilate...

متن کامل

Formant transition-specific adaptation by lipreading of left auditory cortex N1m.

To test for the feature specificity of adaptation of auditory-cortex magnetoencephalographic N1m responses to phonemes during lipreading, we presented eight healthy volunteers with a simplified sine-wave first-formant (F1) transition shared by /ba/, /ga/, and /da/, and a continuum of second-formant (F2) transitions contained in /ba/ (ascending), /da/ (level), and /ga/ (descending), during lipre...

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

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

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2000