Third European Conference on Speech Communication and Technology

Berlin, Germany
September 22-25, 1993


Speaker-Independent Connected Letter Recognition with a Multi-State Time Delay Neural Network

Hermann Hild, Alex Waibel

Universitšt Karlsruhe, Germany Carnegie Mellon University, Pittsburgh, USA

We present a Multi-State Time Delay Neural Network (MS-TDNN) for speaker-independent, connected letter recognition. Our MS-TDNN achieves 98.5/92.0% word accuracy on speaker dependent/independent English letter tasks[7, 8]. In this paper we will summarize several techniques to improve (a) continuous recognition performance, such as sentence level training, and (b) phonetic modeling, such as network architectures with "internal speaker models", allowing for "tuning-in" to new speakers. We also present results on our large and still growing new German Letter data base, containing over 40.000 letters continuously spelled by 55 speakers.

Keywords: Spelled Letter Recognition, Speaker-Independence, MS-TDNN

Full Paper

Bibliographic reference.  Hild, Hermann / Waibel, Alex (1993): "Speaker-independent connected letter recognition with a multi-state time delay neural network", In EUROSPEECH'93, 1481-1484.