زهره انصاری  زهره انصاری  دانشکده فنی و مهندسی
 گروه مهندسی پزشکی  استادیار
 33212456  32353004 (035)
 z_ansari meybod.ac.ir  صفحه شخصی
 Google Scholar

Education

 BSc in Biomedical Engineering, Univirsity of Isfahan, Isfahan, Iran, 2002-2006
 
  • Thesis Title:  Monitoring EMG Signals and Implementing Threshold method for Controlling Artificial Hand 
 
 MSc in Biomedical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran, 2008-2011 
  • Thesis Title: Implementing PCA-based Speaker Adaptation Methods in Speech Recongition Systems
  PhD in Biomedical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran, 2011-2017
  • Thesis Title: Developing Deep Recurrent Neural Networks for Robust Continuous Word Recognition

توسط : saatsaz | تاریخ : 1399/04/18 | نظرات

Publication

  • Journal Publications
1- Zohreh Ansari, Farshad Almasganj, Seyed Jahanshah Kabudian, “Rapid Speaker Adaptation based on Combination of KPCA and Latent Variable Model”, Circuits, Systems, and Signal Processing Journal, 2021
 2- Zohreh Ansari, Seyyed Ali Seyyedsalehi, “Toward Growing Modular Deep Neural Networks for Continuous Speech Recognition”, Neural Processing and Applications Journal, 28 (Suppl 1), 2017, Impact factor: 4.2
 3- Zohreh Ansari, Seyyed Ali Seyyedsalehi, “Deep Modular Neural Network with Double Spatio-Temporal Structure for Persian Continuous Speech Recognition”, Signal and Data Processing Journal, 13(1), 2016 (in Persian)
 4- Sajad Jafari, Zohreh Ansari, Seyyed Mohammad Reza Hashemi Golpayegani, Shahriar Gharibzadeh, “Is Attention a “Period Window” in the Chaotic brain?”, The Journal of neuropsychiatry and clinical neurosciences, 2013, Impact factor: 1.8
  • Conference Publications
1- Z. Ansari, R. Mahmoudi, F. Pourhoseini, End-to-End Speaker Recognition by Deep Convolutional Neural Networks based on Sinc Function, 28th Iranian Conference of Biomedical Engineering, November 2021, Tehran, Iran (in Persian)
2- H. Mir, Z. Ansari,  M.A. Majdian, Classification of White Blood Cell Images Using Pretrained Deep Convolutional Neural Networks, 28th Iranian Conference of Biomedical Engineering, November 2021, Tehran, Iran (in Persian)
3- Z. Ansari, S.A. Seyyedsalehi, “Phone Sequence Modeling Using the Formation of Attractor Dynamics in Recurrent Neural Networks”, 6th Neuroscience Congress 2017, Tehran, Iran
4- Z. Ansari, S.A. Seyyedsalehi, “Proposing Two Speaker Adaptation Methods for Deep Neural Network based Speech Recognition Seytems”, 7th International Symposium on Telecommunications (IST) 2014, Tehran, Iran
5- Z. Ansari, A. Shirudi, S.A. Seyyedsalehi “Implementing of Reservoir Computing Neural Networks in Persian speech recognition”, 22nd Iranian Conference on Biomedical Engineering 2015, Tehran, Iran (in Persian)
6- Z. Ansari, S. Shiri, F. Almasganj, “Analyzing Different MLLR-based Fast Speaker Adaptation Methods in Persian Speech Recognition Systems”, 21st Iranian Conference of Electrical Engineering, May 2013, Mashhad, Iran (in Persian)
7- Z. Ansari, F. Almasganj, "Implementing KPCA based Speaker Adaptation Methods with Different Optimization Algorithms in a Persian ASR System" Procedia-Social and Behavioral Sciences, 32, 2012, pp. 117-127
8- Z. Ansari, F. Almasganj, "Implementing PCA-based Speaker Adaptation Methods in a Persian ASR System", 5th International Symposium on Telecommunications (IST 2010), December 2010, Tehran, Iran
9- Z. Ansari, F. Almasganj, Y. Shekofteh, "Investigating Eigenspace-based Speaker Adaptation Methods in Persian Speech Recognition Systems", 17th Iranian Conference on Biomedical Engineering, Isfahan, Iran (in Persian)

توسط : saatsaz | تاریخ : 1399/04/18 | نظرات

Thesis Supervision

1- Fatemeh Ahmadi, Classification of Mammographic Imgaes by Deep Residual Neural Networks, Meybod University, 2021
2- Mohammd Amin Majdian, Developing a CTC-based end-to-end Speech Recognition System, Meybod University, 2021
3- Shakib Aghili, Implementing Generative Adversarial Networks (GAN) in Image Generation, Meybod University, 2021
4- Zahra Valmohammadi, Investigstion of Different Deep Neural Network Structures in SMR-based BCI, Meybod University, 2021
5- Maryam Ghahremani, Speech Disorder Diagnosis by Recurrent Neural Networks, Meybod University, Ongoing 
6- Hossein Mir, Investigating the Application of Deep CNNs in the Classification of White Blood Cell Images, Meybod University, 2020
7- Amir Pouya Sarhadi Aval, Hand Movement Recognition from EMG signals by Deep Neural Networks, Meybod University, 2020
8- Rasool Mahmoodi, Speaker Recognition Using SincNet-based Convolutional Neural Network, Meybod University, 2020
9- Habib Sanaei, Comparison of LSTM and Reservoir Computing Neural Networks on Speech Recognition, Meybod University, 2020
10- Zeynab Razmi Hamzekhanloo, Investigating the Performance of ReLU activation functions in DNN- based Speech Recognizers, Amirkabir University of Technology. 2015
11- Azadeh Shiroodi, Evaluation of Reservoir Computing Neural Networks in Persian Speech Recognition, Amirkabir University of Technology, 2013

توسط : z_ansari | تاریخ : 1400/10/12 | نظرات

Work Experience

Assistant Professor, Biomedical Engineering Department, Meybod University, Meybod, Yazd, Iran | Fall 2018-Current

  • Teaching courses:Signals and Systems, Medical Equipment, Bioinstrumentation, Medical Imaging, Logic Circuits
  • Supervising different theses, investigating the application of Deep Learning in Signal Processing, Classification, and in Speaker/Speech Recognition

Lecturer, Ragheb Isfahani Higher Education Institute, Isfahan. Iran | Winter 2018

  • Teaching courses: Medical Physics, Medical Imaging

Researcher, Speech Processing and NLU Group, Research Centre of Intelligent Signal Processing, Tehran, Iran | 2011-2013

توسط : saatsaz | تاریخ : 1399/04/18 | نظرات

Skills and Expertise

  • Deep Learning (Designing and training optimum DNNs, CNNs, RNNs (LSTMs, Reservoir Computings), Auto-Encoders, Bidirectional NNs, Chaotic NNs, Attractor NNs)
  • ​Machine Learning (Application of different Classification (LDA, SVM, KNN), Clustering (KMeans, GMM) and Dimension Reduction methods (PCA, KPCA, Auto- Encoders), Hidden Markov Models)
  • ​Speech Recognition (Feature Extraction, Acoustic Modeling(HMM , DNN), Language Modeling (N-gram and RNN-based models), Robustness, Enhancement, Speaker Adaptation)
  • Signal Processing (Random Processes, Data Compression, Estimation: LSE, MAP, ML, Time Series Analysis, Fourier Analysis, Filtering, Wavelet)
     

توسط : saatsaz | تاریخ : 1399/04/18 | نظرات
  • Python and Pytho-based deep learning toolboxes(Tensorflow, Keras, Pytorch)
  • MATLAB and MATLAB-based Toolboxes (DSP and Image Processing, Deep Learning Toolbox)
  • Machine Learning Software Packages (LibSVM, Weka)
  • Speech Processign Toolboxes (HTK, SRILM)