Robust feature extraction in a variety of input devices on the basis of ETSI standard DSR front-end

Satoru Tsuge, Shingo Kuroiwa, Masami Shishibori, Fuji Ren, Kenji Kita

This paper reports an evaluation of European Telecommunications Standards Institute (ETSI) standard Distributed Speech Recognition (DSR) front-end through continuous word recognition on a Japanese speech corpus and proposes a method, the Bias Removal Method (BRM), that reduces the distortion between feature vector and VQ codebook. Experimental results show that using non-quantized features in acoustic model training procedure can improve the recognition performance of DSR front-end features and that the proposed method can improve recognition performances of DSR front-end feature.

doi: 10.21437/ICSLP.2002-605

Cite as: Tsuge, S., Kuroiwa, S., Shishibori, M., Ren, F., Kita, K. (2002) Robust feature extraction in a variety of input devices on the basis of ETSI standard DSR front-end. Proc. 7th International Conference on Spoken Language Processing (ICSLP 2002), 2221-2224, doi: 10.21437/ICSLP.2002-605

@inproceedings{tsuge02_icslp,
  author={Satoru Tsuge and Shingo Kuroiwa and Masami Shishibori and Fuji Ren and Kenji Kita},
  title={{Robust feature extraction in a variety of input devices on the basis of ETSI standard DSR front-end}},
  year=2002,
  booktitle={Proc. 7th International Conference on Spoken Language Processing (ICSLP 2002)},
  pages={2221--2224},
  doi={10.21437/ICSLP.2002-605}
}