A connectionist recognizer for on-line cursive handwriting recognition

Shows how the multi-state time delay neural network (MS-TDNN), which is already used successfully in continuous speech recognition tasks, can be applied both to online single character and cursive (continuous) handwriting recognition. The MS-TDNN integrates the high accuracy single character recognition capabilities of a TDNN with a non-linear time alignment procedure (dynamic time warping algorithm) for finding stroke and character boundaries in isolated, handwritten characters and words. In this approach each character is modelled by up to 3 different states and words are represented as a sequence of these characters. The authors describe the basic MS-TDNN architecture and the input features used in the paper, and present results (up to 97.7% word recognition rate) both on writer dependent/independent, single character recognition tasks and writer dependent, cursive handwriting tasks with varying vocabulary sizes up to 20000 words.<<ETX>>

[1]  Hermann Ney,et al.  The use of a one-stage dynamic programming algorithm for connected word recognition , 1984 .

[2]  Waibel.  A novel objective function for improved phoneme recognition using time delay neural networks , 1989 .

[3]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[4]  Alex Waibel,et al.  Consonant recognition by modular construction of large phonemic time-delay neural networks , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[5]  Alex Waibel,et al.  Integrating time alignment and neural networks for high performance continuous speech recognition , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[6]  Isabelle Guyon,et al.  Design of a neural network character recognizer for a touch terminal , 1991, Pattern Recognit..

[7]  Isabelle Guyon,et al.  Recognition-Based Segmentation of On-Line Hand-Printed Words , 1992, NIPS.

[8]  Alexander H. Waibel,et al.  Speaker-independent connected letter recognition with a multi-state time delay neural network , 1992, EUROSPEECH.

[9]  Ulrich Bodenhausen,et al.  Connectionist architectural learning for high performance character and speech recognition , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[10]  Alexander H. Waibel,et al.  Improving connected letter recognition by lipreading , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[11]  Ulrich Bodenhausen,et al.  Automatically Structured Neural Networks For Handwritten Character And Word Recognition , 1993 .