Portable devices for the consumer market are becoming available in large quantities. Because of their design and use, human speech often is the input modality of choice, for example for car navigation systems or portable speech-to-speech translation devices. In this paper we describe our work in porting our existing desktop PC based speech recognition system to an off-the-shelf PDA running WindowsCE3.0. We do this in a way that our already well performing language and acoustic models can be taken over without the need of retraining them for the PDA. In order to achieve an acceptable run-time behavior we apply several optimization techniques to the preprocessing and decoding process. Among other things we introduce the newly developed early feature vector reduction. In that way the execution time of our recognition system can be reduced from initially 28x real-time to 2.6x real-time with a tolerable increase in word error rate. The size of the acoustic models is reduced to 25% of its original size.
Cite as: Kohler, T.W., Fugen, C., Stüker, S., Waibel, A. (2005) Rapid porting of ASR-systems to mobile devices. Proc. Interspeech 2005, 233-236, doi: 10.21437/Interspeech.2005-116
@inproceedings{kohler05_interspeech,
author={Thilo W. Kohler and Christian Fugen and Sebastian Stüker and Alex Waibel},
title={{Rapid porting of ASR-systems to mobile devices}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={233--236},
doi={10.21437/Interspeech.2005-116}
}