This paper presents a continuous VQ clustering (CVQC) algorithm for realtime speech recognition, which incorporates the temporal information of speech into both training and recognition processes. In comparison with the conventional DTW and VQ methods, this new algorithm delivers faster training and recognition speed and smaller codebook size while still retains merits of both. Realtime impleme...

Face recognition system is one of the intensive research areas in computer vision and pattern recognition but many of which are focused on recognition of faces under various expressions involving many training sample per class. A constrained optical flow algorithm discussed in this paper recognizes facial images involving various expressions under the condition that one single training sample p...

This paper describes a speaker-independent recognition system for continuous German speech based on semicontinuous Hidden-Markov-Models which produces a phonetic transcription of the spoken sentence. The recognition units are parts of syllables while the output is a phoneme level transcription. During recognition, the phonotactic constraints of German are taken into account by a micro syntax co...

BACKGROUND Although impaired recognition of affective facial expressions has been conclusively linked to antisocial behavior, little is known about the modifiability of this deficit. This study investigated whether and under which circumstances the proposed perceptual insensitivity can be addressed with a brief implicit training approach. METHOD Facial affect recognition was assessed with an ...

Face recognition is one of the biometric methods that is used to identify any given face image using the main features of this face. In this research, a face recognition system was suggested based on four Artificial Neural Network (ANN) models separately: feed forward backpropagation neural network (FFBPNN), cascade forward backpropagation neural network (CFBPNN), function fitting neural networ...

Lattice segmentation techniques developed for Minimum Bayes Risk decoding in large vocabulary speech recognition tasks are used to compute the statistics needed for discriminative training algorithms that estimate HMM parameters so as to reduce the overall risk over the training data. New estimation procedures are developed and evaluated for both small and large vocabulary recognition tasks, an...

Tied-mixture HMMs have been proposed as the acoustic model for large-vocabulary continuous speech recognition and have yielded promising results. They share base-distribution and provide more flexibility in choosing the degree of tying than state-clustered HMMs. However, it is unclear which acoustic models to superior to the other under the same training data. Moreover, LBG algorithm and EM alg...

Auditory training has been shown to significantly improve cochlear implant (CI) users' speech and music perception. However, it is unclear whether posttraining gains in performance were due to improved auditory perception or to generally improved attention, memory, and/or cognitive processing. In this study, speech and music perception, as well as auditory and visual memory, were assessed in 10...

We have combined an artificial neural network (ANN) character classifier with context-driven search over character segmentation, word segmentation, and word recognition hypotheses to provide robust recognition of hand-printed English text in new models of Apple Computer's Newton MessagePad. We present some innovations in the training and use of ANNs as character classifiers for word recognition...

Inconsistency between training and testing criteria is a drawback of the hybrid arti cial neural network and hidden Markov model (ANN/HMM) approach to speech recognition. This paper presents an e ective method to address this problem by modifying the feedforward neural network training paradigm. Word errors are explicitly incorporated in the training procedure to achieve improved word recogniti...