A study on data augmentation of reverberant speech for robust speech recognition

Tom Ko, Vijayaditya Peddinti, Daniel Povey, Michael L. Seltzer, Sanjeev KhudanpurICASSP 2017 · OpenReview

Abstract

The environmental robustness of DNN-based acoustic models can be significantly improved by using multi-condition training data. However, as data collection is a costly proposition, simulation of the desired conditions is a frequently adopted strategy. In this paper we detail a data augmentation approach for far-field ASR. We examine the impact of using simulated room impulse responses (RIRs), as real RIRs can be difficult to acquire, and also the effect of adding point-source noises. We find that the performance gap between using simulated and real RIRs can be eliminated when point-source noises are added. Further we show that the trained acoustic models not only perform well in the distant-talking scenario but also provide better results in the close-talking scenario. We evaluate our approach on several LVCSR tasks which can adequately represent both scenarios.
BibTeX
@inproceedings{ko2017study,
  author = {Tom Ko and Vijayaditya Peddinti and Daniel Povey and Michael L. Seltzer and Sanjeev Khudanpur},
  title = {{A study on data augmentation of reverberant speech for robust speech recognition}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2017},
  url = {https://openreview.net/forum?id=f4HYCeAm69},
}

Loading related content...

Figure