Robust speech recognition from ratio masks

Zhong-Qiu Wang, DeLiang WangICASSP 2016 · OpenReview

Abstract

Robustness against noise is crucial for automatic speech recognition systems in real-world environments. In this paper, we propose a novel approach that performs robust ASR by directly recognizing ratio masks. In the proposed approach, a deep neural network (DNN) is first trained to estimate the ideal ratio mask (IRM) from a noisy utterance and then a convolutional neural network (CNN) is employed to recognize estimated IRMs. The proposed approach has been evaluated on the TIDigits corpus, and the results demonstrate that direct recognition of ratio masks outperforms direct recognition of binary masks and traditional MMSE-HMM based method for robust ASR.
BibTeX
@inproceedings{wang2016robust,
  author = {Zhong-Qiu Wang and DeLiang Wang},
  title = {{Robust speech recognition from ratio masks}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2016},
  url = {https://openreview.net/forum?id=nsB4jBZYww1},
}

Loading related content...

Figure