The IARPA BABEL program has stimulated worldwide research in keyword search technology for low resource languages, and the NIST OpenKWS evaluations are the de facto benchmark test for such capabilities. The 2016 OpenKWS evaluation featured Georgian speech, and had 10 participants from across the world. This paper describes the Kaldi system developed to assist IARPA in creating a competitive baseline against which participants were evaluated, and to provide a truly open source system to all participants to support their research. This system handily met the BABEL program goals of 0.60 ATWV and 50% WER, achieving 0.70 ATWV and 38% WER with a single ASR system, i.e. without ASR system combination. All except one OpenKWS participant used Kaldi components in their submissions, typically in conjunction with system combination. This paper therefore complements all other OpenKWS-based papers.
Cite as: Trmal, J., Wiesner, M., Peddinti, V., Zhang, X., Ghahremani, P., Wang, Y., Manohar, V., Xu, H., Povey, D., Khudanpur, S. (2017) The Kaldi OpenKWS System: Improving Low Resource Keyword Search. Proc. Interspeech 2017, 3597-3601, doi: 10.21437/Interspeech.2017-601
@inproceedings{trmal17_interspeech,
author={Jan Trmal and Matthew Wiesner and Vijayaditya Peddinti and Xiaohui Zhang and Pegah Ghahremani and Yiming Wang and Vimal Manohar and Hainan Xu and Daniel Povey and Sanjeev Khudanpur},
title={{The Kaldi OpenKWS System: Improving Low Resource Keyword Search}},
year=2017,
booktitle={Proc. Interspeech 2017},
pages={3597--3601},
doi={10.21437/Interspeech.2017-601}
}