System combination and score normalization for spoken term detection

Jonathan Mamou, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Brian Kingsbury, Kate M. Knill, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlüter, Abhinav Sethy, Philip C. Woodland

Abstract

Spoken content in languages of emerging importance needs to be searchable to provide access to the underlying information. In this paper, we investigate the problem of extending data fusion methodologies from Information Retrieval for Spoken Term Detection on low-resource languages in the framework of the IARPA Babel program. We describe a number of alternative methods improving keyword search performance. We apply these methods to Cantonese, a language that presents some new issues in terms of reduced resources and shorter query lengths. First, we show score normalization methodology that improves in average by 20% keyword search performance. Second, we show that properly combining the outputs of diverse ASR systems performs 14% better than the best normalized ASR system.
BibTeX
@inproceedings{mamou2013system,
  author = {Jonathan Mamou and Jia Cui and Xiaodong Cui and Mark J. F. Gales and Brian Kingsbury and Kate M. Knill and Lidia Mangu and David Nolden and Michael Picheny and Bhuvana Ramabhadran and Ralf Schlüter and Abhinav Sethy and Philip C. Woodland},
  title = {{System combination and score normalization for spoken term detection}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2013},
  doi = {10.1109/icassp.2013.6639278},
}

Loading related content...

Figure