Changes between Version 19 and Version 20 of Other/Summer/2020/AdvML
- Timestamp:
- Jun 29, 2020, 12:12:49 AM (4 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Other/Summer/2020/AdvML
v19 v20 23 23 - Time Delay Neural Network: https://neuron.eng.wayne.edu/tarek/MITbook/chap5/5_4.html 24 24 - Paper: Phoneme Recognition Using Time-Delay Neural Networks (Optional): https://www.orbit-lab.org/attachment/wiki/Other/Summer/2020/AdvML/Phoneme%20Recognition%20Using%20Time-Delay%20Neural%20Networks%20.pdf 25 *Week 5 26 - 1D Convolutional Layer (implementation method for TDNN): https://missinglink.ai/guides/keras/keras-conv1d-working-1d-convolutional-neural-networks-keras/ 27 - Pooling Layer: https://d2l.ai/chapter_convolutional-neural-networks/pooling.html#maximum-pooling-and-average-pooling 28 - Statistical Pooling: https://www.tensorflow.org/api_docs/python/tf/nn/moments 29 - Probabilistic Linear Discriminant Analysis for Inferences About Identity: https://www.orbit-lab.org/attachment/wiki/Other/Summer/2020/AdvML/Probabilistic%20Linear%20Discriminant%20Analysis%20for%20Inferences%20About%20Identity.pdf 30 25 31 == Reading Material == 26 32 - [https://www.orbit-lab.org/attachment/wiki/Other/Summer/2020/AdvML/Hidden%20voice%20commands.pdf Hidden voice commands] … … 30 36 - [https://www.orbit-lab.org/attachment/wiki/Other/Summer/2020/AdvML/Practical%20Adversarial%20Attacks%20Against%20Speaker%20Recognition%20Systems.pdf Practical Adversarial Attacks Against Speaker Recognition Systems] 31 37 - [https://www.orbit-lab.org/attachment/wiki/Other/Summer/2020/AdvML/X-VECTORS-%20ROBUST%20DNN%20EMBEDDINGS%20FOR%20SPEAKER%20RECOGNITION.pdf X-Vectors: Robust DNN Embeddings For Speaker Recognition] 38 39 32 40 == Week 1 Activities == 33 41 … … 57 65 -- (Optional) Learn the concept of Convolutional Neural Network (CNN) and find the similarities between CNN and TDNN. (Note: the implementation of TDNN will be based on one-dimensional CNN.) 58 66 67 == Week 5 Activities == 68 - Learn the steps of using X-Vector model for speaker recognition \\ 69 -- Understand the 1D convolutional layer and use it to implement TDNN \\ 70 -- Understand Statistical Pooling layer \\ 71 -- Classify speakers using Probabilistic Linear Discriminant Analysis (PLDA): trained with the embeddings from the X-vector \\ 72 - Study the Python code samples for X-Vector and implement X-Vector using TensorFlow \\ 73 - Read the paper: Practical Adversarial Attacks Against Speaker Recognition Systems (HotMobile’20) and get familiar with the untargeted attack 74 59 75 == Project Website == 60 76 - [https://chunnubansal.wixsite.com/winlab-amlavas]
