Speaker independent audio-visual continuous speech recognition

Speaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation

A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...

Speaker independent audio-visual database for bimodal ASR

This paper describes the audio-visual database collected at AT&T Labs{Research for the study of bimodal speech recognition. To date, this database consists of two multiple speaker parts, namely isolated confusable words and connected letters, thus allowing the study of some popular and relatively simple speaker independent audio-visual recognition tasks. In addition, a single speaker connected ...

Automatic speechreading of impaired speech

We investigate the use of visual, mouth-region information in improving automatic speech recognition (ASR) of the speech impaired. Given the video of an utterance by such a subject, we first extract appearance-based visual features from the mouth region-of-interest, and we use a feature fusion method to combine them with the subject’s audio features into bimodal observations. Subsequently, we a...

An audio-visual approach to simultaneous-speaker speech recognition

Audio-visual speech recognition is an area with great potential to help solve challenging problems in speech processing. Difficulties due to background noises are significantly reduced by the additional information provided by extra visual features. The presence of additional speech from other talkers during recording may be viewed as one of the most difficult sources of noise. This paper prese...

Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words