CALL (Computer Assisted Language Learning) systems using ASR (Automatic Speech Recognition) for second language learning have received increasing interest recently. However, it st...
We present a variational Bayesian algorithm that enhances the log spectra of noisy speech using speaker dependent priors. This algorithm extends prior work by Frey et al. where th...
When automatic speech recognition (ASR) and speaker verification (SV) are applied in adverse acoustic environments, endpoint detection and energy normalization can be crucial to th...
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
Characteristics of surveillance video generally include low resolution and poor quality due to environmental, storage and processing limitations. It is extremely difficult for comp...
Frank Lin, Clinton Fookes, Vinod Chandran, Sridha ...