3rd Place Solution of AutoSpeech 2019

http://www.4paradigm.com/competition/autospeech2019

Transcript

1. 3rd Place Solution of AutoSpeech 2019
   AutoDL workshop @NeurIPS 2019
   Dec 14, 2019
   Team Kon
   https://github.com/Y-oHr-N/autospeech19
   Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
   

   View Slide

2. Dataset
   Raw speech data
   ● different speech classification domains
   ○ speaker identification
   ○ emotion classification
   ○ accent recognition
   ○ music genre classification
   ○ language identification
   ● single channel
   ● 16 kHz sampling rate
   Meta data
   ● number of classes (is greater than 2 and less than 100)
   ● number of training instances (varies from hundreds to thousands)
   ● time budget (is 1800 seconds for all the datasets)
   2
   Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
   

   View Slide

3. Evaluation
   3
   Metric
   ● area under the learning curve (ALC)
   How to get a high ALC
   ● speed up feature extraction
   ● converge the loss quickly
   ● keep a high AUROC
   Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
   transformed time
   2 * AUROC - 1
   

   View Slide

4. Preprocessing
   4
   crop the first 5 seconds
   raw speech data
   repeat if its length is short
   Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
   

   View Slide

5. Feature extraction
   5
   compute a log mel spectrogram
   Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
   n_dft=1024, n_hop=512, n_mels=64, fmin=20, fmax=8000
   standardize
   Use kapre [Choi+, '17] for fast transformation
   preprocessed speech data
   

   View Slide

6. Data augmentation
   6
   random crop mixup [Zhang+, '17] cutout [DeVries & Taylor, '17]
   Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
   64 px
   64 px
   64 px
   157 px
   

   View Slide

7. Network architecture
   7
   Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
   ReLU
   Dropout-0.5
   Dense-64
   Flatten
   Dense-n
   Softmax
   Conv block
   Conv block
   Conv block
   Input
   Conv block
   Conv block
   Conv block
   Conv2D-64
   ReLU
   BN
   MP2D
   Use the same architecture as the sample code
   

   View Slide

8. Training
   Train with the following settings
   ● initialization: use parameters from pretrained model trained on data01
   ● optimizer: SGD
   ○ lr: 0.01
   ○ momentum: 0.9
   ○ decay: 1e-06
   ● batch size: 32
   Compute the validation score every 5 epochs and resume training if it is not the highest
   ● the ratio of training and validation data is 9:1
   Stop training when the remaining time is less than 0.125 * time_budget
   8
   Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
   

   View Slide

9. Inference
   9
   Make 10 inferences for each speech data and arithmetically average results
   random crop infer average
   result
   result
   Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
   

   View Slide

10. Results of the feedback phase
    10
    Data 11 12 13 14 15
    Domain speaker emotion accent music language
    Rank 2 2 1 3 3
    ALC 0.8997 0.6013 0.8420 0.5620 0.8703
    2 * AUROC - 1 0.9916 0.7154 0.9775 0.5972 0.9980
    Curve
    Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
    

    View Slide

11. Data 21 22 23 24 25
    Domain speaker emotion accent music language
    Rank 3 4 1 4 4
    ALC 0.9477 0.7597 0.9132 0.6588 0.8572
    2 * AUROC - 1 1.0000 0.8273 0.9776 0.7166 0.9835
    Curve
    Results of the final phase
    11
    Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
    

    View Slide

12. Conclusion
    12
    Successful work
    ● feature extraction using kapre
    ● pretrained model
    ● data augmentation
    Unsuccessful work
    ● complex network architecture like EfficientNet [Tan & Le, '19]
    Future work
    ● automated data augmentation
    Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
    

    View Slide

13. References
    13
    Choi, K., Joo, D., and Kim, J.,
    "Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with
    Keras."
    In arXiv, 2017.
    DeVries, T., and Taylor G. W.,
    "Improved Regularization of Convolutional Neural Networks with Cutout."
    In arXiv, 2017.
    Tan, M., and Le, Q. V.,
    "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks."
    In Proceedings of ICML, pp. 6105-6114, 2019.
    Zhang, H., Cisse, M., Dauphin, Y. N., and Lopez-Paz, D.,
    "mixup: Beyond Empirical Risk Minimization."
    In Proceedings of ICLR, 2018.
    Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
    

    View Slide

14. NS Solutions and NS logo are registered trademarks of NS Solutions Corporation
    14
    Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
    

    View Slide