Cascade processing for speeding up sliding window sparse classification. Mahkonen, K., Hurmalainen, A., Virtanen, T., & Kämäräinen, J. In 2016 24th European Signal Processing Conference (EUSIPCO), pages 2305-2309, Aug, 2016.
Cascade processing for speeding up sliding window sparse classification [pdf]Paper  doi  abstract   bibtex   
Sparse representations have been found to provide high classification accuracy in many fields. Their drawback is the high computational load. In this work, we propose a novel cascaded classifier structure to speed up the decision process while utilizing sparse signal representation. In particular, we apply the cascaded decision process for noise robust automatic speech recognition task. The cascaded decision process is implemented using a feedforward neural network (NN) and time sparse versions of a non-negative matrix factorization (NMF) based sparse classification method of [1]. The recognition accuracy of our cascade is among the three best in the recent CHiME2013 benchmark and obtains six times faster the accuracy of NMF alone as in [1].
@InProceedings{7760660,
  author = {K. Mahkonen and A. Hurmalainen and T. Virtanen and J. Kämäräinen},
  booktitle = {2016 24th European Signal Processing Conference (EUSIPCO)},
  title = {Cascade processing for speeding up sliding window sparse classification},
  year = {2016},
  pages = {2305-2309},
  abstract = {Sparse representations have been found to provide high classification accuracy in many fields. Their drawback is the high computational load. In this work, we propose a novel cascaded classifier structure to speed up the decision process while utilizing sparse signal representation. In particular, we apply the cascaded decision process for noise robust automatic speech recognition task. The cascaded decision process is implemented using a feedforward neural network (NN) and time sparse versions of a non-negative matrix factorization (NMF) based sparse classification method of [1]. The recognition accuracy of our cascade is among the three best in the recent CHiME2013 benchmark and obtains six times faster the accuracy of NMF alone as in [1].},
  keywords = {feedforward neural nets;matrix decomposition;signal classification;signal representation;speech recognition;sliding window sparse classification;cascaded classifier structure;sparse signal representation;cascaded decision process;noise robust automatic speech recognition;feedforward neural network;nonnegative matrix factorization based sparse classification;NMF;cascade processing;Artificial neural networks;Signal processing;Grammar;Europe;Automatic speech recognition;Sparse matrices;Speech;Automatic speech recognition;non-negative matrix factorization;cascade classification;cascade processing},
  doi = {10.1109/EUSIPCO.2016.7760660},
  issn = {2076-1465},
  month = {Aug},
  url = {https://www.eurasip.org/proceedings/eusipco/eusipco2016/papers/1570252399.pdf},
}
Downloads: 0