A technique is presented which combines rule-based and neural network pattern recognition methods in an integrated system in order to perform learning and recognition of hand-written characters and gestures in realtime. The GesRec system is introduced which provides a framework for data acquisition, training, recognition, and gesture-to-speech transcription in a Windows environment. A recogniti...

We perform language identification experiments for four prominent South-African languages using a multilingual speech recognition system. Specifically, we show how successfully Afrikaans, English, Xhosa and Zulu may be identified using a single set of HMMs and a single recognition pass. We further demonstrate the effect of language identification-specific discriminative acoustic model training ...

Real-world applications using speech recognition must perform well over a range of dialects. Di erences in dialect between the speakers in the training database and the target users often leads to degraded recognition performance. For the BBN Hark Hidden Markov Model (HMM) based system, we have already developed a reasonably e ective technique [1] for dealing with multiple US dialects. The solu...

This paper investigates the use of a large corpus for the training of a Broadcast News speech recognizer. A vast body of speech recognition algorithms and mathematical machinery is aimed at smoothing estimates toward accurate modeling with scant amounts of data. In most cases, this research is motivated by a real need for more data. In Broadcast News, however, a large corpus is already availabl...

This paper presents a hidden Markov model (HMM) based approach to on-line handwritten digit recognition using stroke sequences. In this approach, a character instance is represented by a sequence of symbolic strokes, and the representation is obtained by component segmentation and stroke classification. The component segmentation is based on the delta lognormal model of handwriting generation. ...

One of the major hurdles in the development of an Automatic Spontaneous Speech Recognition System is the unavailability of large amounts of transcribed spontaneous speech data for training the system. On the other hand transcribed read speech data is available comparatively easily. This paper explores the possibilities of training a spontaneous speech recognition system by using a mixture of re...

Discriminative training of hidden Markov models (HMMs) using segmental minimum classi cation error (MCE) training has been shown to work extremely well for certain speech recognition applications. It is, however, somewhat prone to overspecialization. This study investigates various techniques which improve performance and generalization of the MCE algorithm. Improvements of up to 7% in relative...

Discriminative training techniques for Hidden Markov Models were recently proposed and successfully applied for automatic speech recognition In this paper a discussion of the Minimum Classi cation Error and the Maximum Mu tual Information objective is presented An extended reesti mation formula is used for the HMM parameter update for both objective functions The discriminative training me thod...

Adult learners of Chinese learned new characters through writing, visual chunking or reading-only. Following training, ERPs were recorded during character recognition tasks, first shortly after the training and then three months later. We hypothesized that the character training effects would be seen in ERP components associated with word recognition and episodic memory. Results confirmed a lar...

In this paper, a Handwritten Character Recognition system is designed using Multilayer Feedforward Articial Neural Networks. Backpropagation Learning algorithm is prefered for training of neural network. Training set occures of various Latin characters collected from different people. The characters are presented directly to the network and correctly sized in pre-processing. Recognition percent...