ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Bounded conditional mean imputation with an approximate posterior

Ulpu Remes

Missing-feature imputation or reconstruction is used in noiserobust automatic speech recognition to recover the unobserved clean speech information. Reconstruction methods often use the noise-corrupted observations and a clean speech prior to calculate a point estimate for the unobserved clean speech features, whereas the approach proposed in this work associates the unobserved clean speech features with a full posterior distribution. The posterior mean can be used as a clean speech estimate in bounded conditional mean imputation and the posterior variance can be included as observation uncertainties. The proposed method is evaluated in a large-vocabulary noise-robust speech recognition task with speech data recorded in real noisy environments.

doi: 10.21437/Interspeech.2013-279

Cite as: Remes, U. (2013) Bounded conditional mean imputation with an approximate posterior. Proc. Interspeech 2013, 3007-3011, doi: 10.21437/Interspeech.2013-279

  author={Ulpu Remes},
  title={{Bounded conditional mean imputation with an approximate posterior}},
  booktitle={Proc. Interspeech 2013},