Evaluating robust features on deep neural networks for speech recognition in noisy and channel mismatched conditions

@inproceedings{Mitra2014EvaluatingRF,
  title={Evaluating robust features on deep neural networks for speech recognition in noisy and channel mismatched conditions},
  author={Vikramjit Mitra and Wen Wang and Horacio Franco and Yun Lei and Chris Bartels and Martin Graciarena},
  booktitle={INTERSPEECH},
  year={2014}
}
Deep Neural Network (DNN) based acoustic models have shown significant improvement over their Gaussian Mixture Model (GMM) counterparts in the last few years. While several studies exist that evaluate the performance of GMM systems under noisy and channel degraded conditions, noise robustness studies on DNN systems have been far fewer. In this work we… CONTINUE READING

6 Figures & Tables

Statistics

01020201620172018
Citations per Year

Citation Velocity: 10

Averaging 10 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.