A high-performance Cantonese keyword search system

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

Abstract

We present a system for keyword search on Cantonese conversational telephony audio, collected for the IARPA Babel program, that achieves good performance by combining postings lists produced by diverse speech recognition systems from three different research groups. We describe the keyword search task, the data on which the work was done, four different speech recognition systems, and our approach to system combination for keyword search. We show that the combination of four systems outperforms the best single system by 7%, achieving an actual term-weighted value of 0.517.
BibTeX
@inproceedings{kingsbury2013high,
  author = {Brian Kingsbury and Jia Cui and Xiaodong Cui and Mark J. F. Gales and Kate M. Knill and Jonathan Mamou and Lidia Mangu and David Nolden and Michael Picheny and Bhuvana Ramabhadran and Ralf Schlüter and Abhinav Sethy and Philip C. Woodland},
  title = {{A high-performance Cantonese keyword search system}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2013},
  doi = {10.1109/icassp.2013.6639279},
}

Loading related content...

Figure