Spoken Term Detection Using Multiple Speech Recognizers' Outputs at NTCIR-9 SpokenDoc STD subtask

@inproceedings{Nishizaki2011SpokenTD,
  title={Spoken Term Detection Using Multiple Speech Recognizers' Outputs at NTCIR-9 SpokenDoc STD subtask},
  author={Hiromitsu Nishizaki and Yuto Furuya and Satoshi Natori and Yoshihiro Sekiguchi},
  booktitle={NTCIR},
  year={2011}
}
This paper describes spoken term detection (STD) with false detection control using a phoneme transition network (PTN) derived from multiple speech recognizers’ outputs at NTCIR9 SpokenDoc STD subtask. Using the output of multiple speech recognizers, the PTN method is effective at correctly detecting out-of-vocabulary (OOV) terms and is robust to certain recognition errors. However, it exhibits a high false detection rate. Therefore, we applied two false detection control parameters to the… CONTINUE READING