Large vocabulary speaker independent isolated word recognition for embedded systems

In this paper the implementation of a word-stem based tree search for large vocabulary speaker independent isolated word recognition for embedded systems is presented. Two fast search algorithms combine the effectiveness of the tree structure for large vocabularies and the fast Viterbi search within the regular structures of word-stems. The algorithms are proved to be very effective for workstation and embedded platform realizations. In order to decrease the processing power the word-stem based tree search with frame dropping approach is used. The recognition speed was increased by a factor of 5 without frame dropping and by a factor of 10 with frame dropping in comparison to linear Viterbi search for isolated word recognition task with a vocabulary of 20102 words. Thus, the large vocabulary isolated word recognition becomes possible for embedded systems.

[1]  Josef G. Bauer,et al.  High performance speaker and vocabulary independent ASR technology for mobile phones , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[2]  Benoît Maison,et al.  A robust high accuracy speech recognition system for mobile applications , 2002, IEEE Trans. Speech Audio Process..

[3]  Hermann Ney,et al.  A comparison of two LVR search optimization techniques , 2002, INTERSPEECH.

[4]  Alfred Hauenstein.  Architecture of a 10, 000 word real time speech recognizer , 1993, EUROSPEECH.

[5]  Hans J. G. A. Dolfing.  Transducer search space modelings for large-vocabulary speech recognition , 2002, INTERSPEECH.