We present an MS-TDNN for recognizing continuously spelled letters, a task characterized by a small but highly confusable vocabulary. We pro(cid:173) pose training techniques aimed at improving sentence level perfor(cid:173) mance, including free alignment across word boundaries, word du(cid:173) ration modeling and error backpropagation on the sentence rather than the word level. Architectures integrating submodules special(cid:173) ized on a subset of speakers achieved further improvements.

This system combines a robust input representation, which preserves the dynamic writing information, with a neural network architecture, a so called Multi-State Time Delay Neural Network (MS-TDNN), which integrates rec.ognition and segmentation in a single framework. Our preprocessing transforms the original coordinate sequence into a (still temporal) sequence offeature vectors, which combine strictly local features, like curvature or writing direction, with a bitmap-like representation of the coordinate's proximity. The MS-TDNN architecture is well suited for handling temporal sequences as provided by this input representation. Our system is tested both on writer dependent and writer independent tasks with vocabulary sizes ranging from 400 up to 20,000 words. For example, on a 20,000 word vocabulary we achieve word recognition rates up to 88.9% (writer dependent) and 84.1 % (writer independent) without using any language models.

This system combines a robust input representation, which preserves the dynamic writing information, with a neural network architecture, a so called Multi-State Time Delay Neural Network (MS-TDNN), which integrates rec.ognition and segmentation in a single framework. Our preprocessing transforms the original coordinate sequence into a (still temporal) sequence offeature vectors, which combine strictly local features, like curvature or writing direction, with a bitmap-like representation of the coordinate's proximity. The MS-TDNN architecture is well suited for handling temporal sequences as provided by this input representation. Our system is tested both on writer dependent and writer independent tasks with vocabulary sizes ranging from 400 up to 20,000 words. For example, on a 20,000 word vocabulary we achieve word recognition rates up to 88.9% (writer dependent) and 84.1 % (writer independent) without using any language models.

This system combines a robust input representation, which preserves the dynamic writing information, with a neural network architecture, a so called Multi-State Time Delay Neural Network (MS-TDNN), which integrates rec.ognition and segmentation ina single framework. Our preprocessing transforms the original coordinate sequence into a (still temporal) sequence offeature vectors,which combine strictly local features, like curvature or writing direction, with a bitmap-like representation of the coordinate's proximity.The MS-TDNN architecture is well suited for handling temporal sequences as provided by this input representation. Oursystem is tested both on writer dependent and writer independent tasks with vocabulary sizes ranging from 400 up to 20,000 words. For example, on a 20,000 word vocabulary we achieve word recognition rates up to 88.9% (writer dependent) and 84.1 % (writer independent) without using any language models.

We present an MS-TDNN for recognizing continuously spelled letters, a task characterized by a small but highly confusable vocabulary.

We present an MS-TDNN for recognizing continuously spelled letters, a task characterized by a small but highly confusable vocabulary.

We present an MS-TDNN for recognizing butcontinuously spelled letters, a task characterized by a small highly confusable vocabulary.

We present the "Multi-State Time Delay Neural Network" (MS-TDNN) as an extension of the TDNN to robust word recognition.

We present the "Multi-State Time Delay Neural Network" (MS-TDNN) as an extension of the TDNN to robust word recognition.

We present the "Multi-State Time Delay Neural Network" (MS-TDNN) as an extension of the TDNN to robust word recognition.