ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

Comparative evaluations of several front-ends for robust speech recognition

Doh-Suk Kim, Jae-Hoon Jeong, Soo-Young Le, Rhee M. Kil

Zero-crossings with peak amplitudes (ZCPA) model motivated by human auditory periphery is simple com- pared with other auditory models, but powerful speech analysis tool for robust speech recognition in noisy environments. In this paper, improvement in recog- nition rate of ZCPA model is addressed by incorpo- rating time-derivative features with several different time-derivative window lengths. Experimental results show that ZCPA has relatively higher sensitivity to derivative window length than conventional feature extraction algorithms. Also, experimental compar- isons with several front-ends including some auditory- like schemes in real-world noisy environments demon- strate the robustness of ZCPA model. ZCPA model shows superior performance compared with other front- ends especially in noisy condition corrupted by white Gaussian noise.


doi: 10.21437/Eurospeech.1997-118

Cite as: Kim, D.-S., Jeong, J.-H., Le, S.-Y., Kil, R.M. (1997) Comparative evaluations of several front-ends for robust speech recognition. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 1135-1138, doi: 10.21437/Eurospeech.1997-118

@inproceedings{kim97c_eurospeech,
  author={Doh-Suk Kim and Jae-Hoon Jeong and Soo-Young Le and Rhee M. Kil},
  title={{Comparative evaluations of several front-ends for robust speech recognition}},
  year=1997,
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
  pages={1135--1138},
  doi={10.21437/Eurospeech.1997-118},
  issn={1018-4074}
}