Integrated DNN-based model adaptation technique for noise-robust speech recognition

Kang Hyun Lee, Woo Hyun Kang, Tae Gyoon Kang, Nam Soo KimICASSP 2017 · OpenReview

Abstract

Since the introduction of deep neural network (DNN)-based acoustic model, robust automatic speech recognition using DNN are being in research. Especially in model adaptation, the techniques utilizing auxiliary context features is known to be a promising technique. Recently, we proposed a technique which is called two-stage noise-aware training (TSNAT). The key idea of TS-NAT is to let the DNN clarify the relationship among noise estimate, noisy features and phonetic target through clean feature representation. However, although TS-NAT enhances the robustness of the DNN, we cannot be certain whether TS-NAT describes the clean feature representation sufficiently. In this paper, we extend TS-NAT using true noise feature and various DNN training techniques. It has been shown that the proposed technique outperforms the conventional DNN-based techniques on Aurora5-task and mismatched noise conditions.
BibTeX
@inproceedings{lee2017integrated,
  author = {Kang Hyun Lee and Woo Hyun Kang and Tae Gyoon Kang and Nam Soo Kim},
  title = {{Integrated DNN-based model adaptation technique for noise-robust speech recognition}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2017},
  url = {https://openreview.net/forum?id=VQwCYdJZFj},
}

Loading related content...

Figure