Switching linear dynamic transducer for stereo data based speech feature mapping

Chang Woo Han, Tae Gyoon Kang, Doo Hwa Hong, Nam Soo Kim, Kiwan Eom, Jaewon LeeICASSP 2011 · OpenReview

Abstract

The performance of a speech recognition system may be degraded even without any background noise because of the linear or non-linear distortions incurred by recording devices or reverberations. One of the well-known approaches to reduce this channel distortion is feature mapping which maps the distorted speech feature to its clean counterpart. The feature mapping rule is usually trained based on a set of stereo data which consists of the simultaneous recordings obtained in both the reference and target conditions. In this paper, we propose a novel approach to speech feature sequence mapping based on the switching linear dynamic transducer (SLDT). The proposed algorithm enables us a sequence-to-sequence mapping in a systematic way, instead of the traditional vector-to-vector mapping. The proposed approach is applied to compensate channel distortion in speech recognition and shows improvement in recognition performance.
BibTeX
@inproceedings{han2011switching,
  author = {Chang Woo Han and Tae Gyoon Kang and Doo Hwa Hong and Nam Soo Kim and Kiwan Eom and Jaewon Lee},
  title = {{Switching linear dynamic transducer for stereo data based speech feature mapping}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2011},
  url = {https://openreview.net/forum?id=ryyIOugXxa},
}

Loading related content...

Figure