SANAZ SEYEDIN - Amirkabir University of Technology

Educational Records

#

Degree/Major

University

City

Country

Graduation Date

1

B.S

Amirkabir University of Technology (Tehran Polytechnic)

Tehran

Iran

December 2001

2

Post-doctoral fellow

University of Sherbrooke

Sherbrooke, QC

Canada

June 2012

3

Ph.D

Amirkabir University of Technology (Tehran Polytechnic)

Tehran

Iran

October 2010

4

Visiting Research Student

Queen's University

Kingston, ON

Canada

October 2010

5

M.S

Iran University of Science and Technology

Tehran

Iran

September 2005

Supervised MSc Theses

#

Thesis title

By

Date

1

Customers satisfaction analysis from online shopping in social networks using sentiment analysis and text mining

ANAHITA AKBARZADEH

2024 Sep

2

Text sentiment analysis with deep neural networks

POUYA AHADI

2024 May

3

speech emotion recognition using deep neural networks based on reinforcement learning

ALIREZA RAHMATI

2024 Jan

4

Speech Emotion Recognition Using Autoencoder

ZAHRA SHARIFZADEH JAFARI

2024 Jan

5

improving the design and implementation of block ciphers with random key generation algorithms based on biometric methods

MOHAMADREZA ROOZBAHANI

2023 Jul

6

Human action recognition in still images using Deep Networks

SEYED ROHOLLAH HOSSEYNI & HASSAN TAHERI

2023 Mar

7

Smart phone based colorimetric detection of glucose for paper-based microfluidics sensor via machine learning

SOLALEH GHATEII & Amir Jahanshahi

2022 Jul

8

Persian Text Summarization Using Deep Learning

AMIRHOSSEIN BAYAT

2022 Feb

9

Speech emotion recognition with deep learning netwotks

ALIREZA TAHERINAVID

2022 Feb

10

Quality improvement of speech source separation methods by deep learning

FATEMEH NOURIAN FARKOOSH

2021 Oct

11

Open domain question answering system in the Persian language using deep learning

SEYEDEH MELIKA EMAMI

2021 Oct

12

Hand motions recognition from EMG signals recorded by dry and flexible electrodes

MARYAM FAZELI

2021 Sep

13

Designing an Ensemble Learning Model for Customer Churn

NASTARAN JAVANI & JAMAL SHAHRABI

2021 Sep

14

3D layout recovery from 360 images

ARIAN SABAGHI KHAMENEH & HASSAN TAHERI

2021 Aug

15

Speech Enhancement Based on Deep Learning Methods and the Evaluation of Using Complex Spectrum to Improve the Results

MOHAMMAD SAEID DEYLAMI

2020 Jul

16

Speech Enhancement with deep learning methods using kernel decomposition techniques

MOHAMMAD MAHDI MIRJALILI

2020 Jun

17

speech source separation using deep neural networks

SEYEDMAJID NOORANI

2020 Feb

18

Single-channel Speaker Extraction Based on Deep Learning

HALEH DAMIRCHI

2020 Feb

19

Robust voice activity detection using Neural Network

IMAN SHAHRIARI

2020 Feb

20

Speech enhancement using nonnegative matrix factorization

HAMID REZA ASJODI MOGHADDAM

2020 Feb

21

Human Activity Recognition using Fused Wearable Sensors and Social Media Based on Distributed Machine Learning on the Platform of Big Data

ALIREZA KESHAVARZIAN & SAEED SHARIFIAN KHORTOOMI

2019 Feb

22

Speech emotion recognition based on appropriate kernel decomposition

MILAD LASHKARI

2018 Oct

23

Noise reduction of speech signals using deep neural networks

RAZIEH SAFARI & S.M. AHADI SARKANI

2017 Sep

24

Vegetation Identification Using Satellite Imagery and Machine Learning Method

SEYEDMOHAMMADREZA HAGHI

2026 May

25

Changes Detection of land in regional and plant coverage using deep learning

MARZIYEH MOHAMMADMOMEN

2026 Jun

26

EEG-based Detection Of Autism Using Feature Extraction And Deep Learning Algorithms

Ali Jalili & HASSAN TAHERI

2025 Sep

27

Human-music emotional interaction based on text sentiment analysis with deep learning

SEYED ALI SHAHCHERAGH

2025 May

28

Emotional Sentiment Analysis from EEG Signals Using Deep Learning Techniques

MOHAMMAD BARATI DEHAGHI

2025 Mar

Journal Papers

1

PASHAIAN MATIN ، SEYEDIN SANAZ, "Multiple transformer-based models for phase-sensitive masking-based single-channel speech enhancement", Caai Transactions On Intelligence Technology, 2026 May vol. 12, no. , pp.1-14, 2026.

2

RAHMATI ALIREZA ، SEYEDIN SANAZ ، SHARIFZADEH JAFARI ZAHRA, "Persian Aut emotional speech database: machine learning-based evaluation and cost-efficient labeling approach", Multimedia Systems, 2026 Feb vol. 32, no. 90, pp.1-23, 2026.

3

AMIRAN AMIRMASOUD ، BEHNAM BEHROUZ ، SEYEDIN SANAZ, "Machine Learning for Earthquake Emergency Evacuation: Site Selection and Neighborhood Navigation", Ieee Access, 2025 May vol. 13, no. , pp.91595-91610, 2025.

4

AMIRAN AMIRMASOUD ، BEHNAM BEHROUZ ، SEYEDIN SANAZ, "AI-Based model for site-selecting earthquake emergency shelters", Scientific Reports, 2024 Nov vol. 14, no. 29033, pp.1-20, 2024.

5

PASHAIAN MATIN ، SEYEDIN SANAZ, "Speech enhancement based on a joint two-stage CRN+DNN-DEC model and a new constrained phase-sensitive magnitude ratio mask", Ieee Access, 2024 Jul vol. 0, no. 0, pp.1-17, 2024.

6

SHARIFZADEH JAFARI ZAHRA ، SEYEDIN SANAZ, "A novel multi-task and ensembled optimized parallel convolutional autoencoder and transformer for speech emotion recognition", Aut Journal of Electrical Engineering, 2024 Mar vol. 56, no. 2, pp.213-226, 2024.

7

PASHAIAN MATIN ، SEYEDIN SANAZ, "Speech enhancement using Joint DNN-NMF model learned with multi-objective frequency differential spectrum loss function", Iet Signal Processing, 2024 Jan vol. 2024, no. 1, pp.1-10, 2024.

8

SAFARI DEHNAVI RAZIEH ، SEYEDIN SANAZ, "NMF-based Improvement of DNN and LSTM Pre-Training for Speech Enhancement", International Journal of Information and Communication Technology(Ijict), 2023 Sep vol. 15, no. 3, pp.53-65, 2023.

9

ROOZBAHANI MOHAMADREZA ، SEYEDIN SANAZ ، Bahram Rashidi, "A new method to generate a biometric encryption key based on a segmented fingerprint image", , 2023 Jun vol. 10, no. 2, pp.1-18, 2023.

10

PASHAIAN MATIN ، SEYEDIN SANAZ ، AHADI SARKANI S.M., "A novel jointly-optimized cooperative DAE-DNN approach based on a new multi-target step-wise learning for speech enhancement", Ieee Access, 2023 Mar vol. 0, no. 0, , 2023.

11

SHAHEDI ALI ، SEYEDIN SANAZ, "ChatParse: A New Application for Persian Bourse Chatbot", International Journal of Information and Communication Technology(Ijict), 2023 Mar vol. 15, no. 2, pp.49-58, 2023.

12

DAMIRCHI HALEH ، SEYEDIN SANAZ ، AHADI SARKANI S.M., "Improving the loss function efficiency for speaker extraction using psychoacoustic effects", Applied Acoustics, 2021 Dec vol. 183, no. 1, pp.1-7, 2021.

13

KESHAVARZIAN ALIREZA ، SHARIFIAN KHORTOOMI SAEED ، SEYEDIN SANAZ, "Modified deep residual network architecture deployed on serverless framework of IoT platform based on human activity recognition application", Future Generation Computer Systems-The International Journal of Escience, 2019 Jun vol. 101, no. 0, pp.14-28, 2019.

14

Nastaran Borjian ، Ehsanollah Kabir ، SEYEDIN SANAZ ، Ellips Masehian, "A query-by-example music retrieval system using feature and decision fusion", Multimedia Tools and Applications, 2018 Mar vol. 77, no. 5, pp.6165-6169, 2018.

15

Mohammadali Azamian ، Ehsanollah Kabir ، SEYEDIN SANAZ ، Ellips Masehian, "An Adaptive sparse algorithm for synthesizing note specific atoms by spectrum analysis, applied to music signal separation", Advances In Electrical and Computer Engineering, 2017 May vol. 17, no. 2, pp.103-112, 2017.

16

MAVADDATI SAMIRA ، AHADI SARKANI S.M. ، SEYEDIN SANAZ, "Speech enhancement using sparse dictionary learning in wavelet packet transform domain", Computer Speech and Language, 2017 Feb vol. 0, no. 0, , 2017.

17

RIAZATI SERESHT HAMED ، AHADI SARKANI S.M. ، SEYEDIN SANAZ, "Spectro-temporal Power Spectrum Features for Noise Robust ASR", Circuits Systems and Signal Processing, 2016 Nov vol. 35, no. 0, , 2016.

18

Nastaran Borjian ، Ehsanollah Kabir ، SEYEDIN SANAZ ، Ellips Masehian, "Query-by-example music retrieval using genre recognition to speed up the performance", Journal of Acoustical Engineering Society of Iran, 2016 Sep vol. 4, no. 1, pp.1-20, 2016.

19

MAVADDATI SAMIRA ، AHADI SARKANI S.M. ، SEYEDIN SANAZ, "A Novel speech enhancement method by learnable sparse and low-rank decomposition and domain adaptation", Speech Communication, 2016 Feb vol. 76, no. 1, pp.42-60, 2016.

20

MAVADDATI SAMIRA ، AHADI SARKANI S.M. ، SEYEDIN SANAZ, "Modified coherence-based dictionary learning method for speech enhancement", Iet Signal Processing, 2015 Sep vol. 9, no. 7, pp.537-545, 2015.

21

SEYEDIN SANAZ ، Saeed Gazor ، AHADI SARKANI S.M., "On the distribution of Mel-filtered log-spectrum of Speech in additive noise", Speech Communication, 2015 Mar vol. 67, no. 1, pp.8-25, 2015.

22

SEYEDIN SANAZ ، AHADI SARKANI S.M. ، Saeed Gazor, "New features using robust MVDR spectrum of filtered autocorrelation sequence for robust speech recognition", Scientific World Journal, 2013 Nov vol. 2013, no. 634160, pp.1-11, 2013.

23

SEYEDIN SANAZ ، AHADI SARKANI S.M., "A New subband-weighted MVDR-based front-end for robust speech recognition", Ieice Transactions On Information and Systems, 2010 Jul vol. , no. 8, pp.2252-2261, 2010.

1

S. Mavaddati, S. M. Ahadi, S. Seyedin, "Modified coherence-based dictionary learning method for speech enhancement", Iet Signal Processing, 2015 vol. 9, no. 7, pp.537-545, 2015.

2

S. Seyedin, S. Gazor, S. M. Ahadi, "On the distribution of Mel-filtered log-spectrum of Speech in additive noise", Speech Communication, 2015 vol. 67, no. , pp.8-25, 2015.

3

S. Seyedin, S. M. Ahadi, S. Gazor, "New features using robust MVDR spectrum of filtered autocorrelation sequence for robust speech recognition", The Scientific World Journal, 2013 vol. 2013, no. , pp.1-11, 2013.

4

S. Seyedin, S. M. Ahadi, "A New subband-weighted MVDR-based front-end for robust speech recognition", Ieice Transactions On Information and Systems, 2010 vol. E93-D, no. 8, pp.2252-2261, 2010.

Conference Papers

1

HOSSEYNI SEYED ROHOLLAH ، Ali Ahmad Rahmani ، Seyed Jamal Seyedmohammadi ، SEYEDIN SANAZ ، Arash Mohammadi, "BAD: Bidirectional Auto-Regressive Diffusion for Text-to-Motion Generation,", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2025.

2

HOSSEYNI SEYED ROHOLLAH ، SEYEDIN SANAZ ، TAHERI HASSAN, "Human Action Recognition in Still Images Using ConViT,", 32nd International Conference on Electrical Engineering, May 2024.

3

DAMIRCHI HALEH ، SEYEDIN SANAZ ، AHADI SARKANI S.M., "Speaker extraction using BLSTM optimized with a new loss function based on differentiated spectrum in frequency domain,", 28th Iranian Conference on Electrical Engineering (ICEE), Aug 2020.

4

DEYLAMI MOHAMMAD SAEID ، SEYEDIN SANAZ, "Fusion of amplitude and complex domains based on deep neural networks for speech enhancement,", 28th Iranian Conference on Electrical Engineering (ICEE), Aug 2020.

5

ASJODI MOGHADDAM HAMID REZA ، SEYEDIN SANAZ, "Modular NMF and DNN speech enhancement approach with update noise,", 28th Iranian Conference on Electrical Engineering (ICEE), Aug 2020.

6

SHAHRIARI IMAN ، SEYEDIN SANAZ ، AHADI SARKANI S.M., "Robust voice activity detection based on complementary BLSTM enhancement stage,", 28th Iranian Conference on Electrical Engineering (ICEE), Aug 2020.

7

NOORANI SEYEDMAJID ، SEYEDIN SANAZ, "Single channel speech source separation using hierarchical deep neural networks,", 28th Iranian Conference on Electrical Engineering (ICEE), Aug 2020.

8

MIRJALILI MOHAMMAD MAHDI ، SEYEDIN SANAZ, "Speech enhancement using NMF based on hierarchical deep neural networks with joint learning,", 28th Iranian Conference on Electrical Engineering (ICEE), Aug 2020.

9

FAZELI MARYAM ، KARIMI FARANAK ، RAMEZANIAN VIDA ، Jahanshahi Amir ، SEYEDIN SANAZ, "Hand Motion Classification Using sEMG Signals Recorded from Dry and Wet Electrodes with Machine Learning,", 28th Iranian Conference on Electrical Engineering (ICEE), Aug 2020.

10

DANAYI ABOLFAZL ، SEYEDIN SANAZ, "A novel algorithm based on time-frequency analysis for extracting melody from human whistling,", 4th Iranian Conference of Signal Processing and Intelligent Systems, Dec 2018.

11

LASHKARI MILAD ، SEYEDIN SANAZ, "NMF-based cepstral features for speech emotion recognition,", 4th Iranian Conference of Signal Processing and Intelligent Systems, Dec 2018.

12

DASTGHEIB SEYYED MOHAMMADALI ، SEYEDIN SANAZ, "Vessel segmentation in coloured retinal fundus images based on multi-scale analysis,", 4th Iranian Conference of Signal Processing and Intelligent Systems, Dec 2018.

13

ALISAMIR SINA ، AHADI SARKANI S.M. ، SEYEDIN SANAZ, "An end-to-end deep learning model to recognize Farsi speech from raw input,", 4th Iranian Conference of Signal Processing and Intelligent Systems, Dec 2018.

14

JAZLAEIYAN MOHAMMAD ، SEYEDIN SANAZ ، MOTAMEDI S.AHMAD, "Enhanced brain inspired model for face categorization using mutual information maximization,", 25th Iranian Conference on Biomedical Engineering and 2018 3rd International Iranian Conference on Biomedical Engineering, Nov 2018.

15

Mojtaba Bahrami ، SEYEDIN SANAZ, "MMSE log-spectral amplitude estimation for single channel speech enhancement under speech presence uncertainty by Weibull speech priors,", 26th Iranian Conference on Electrical Engineering, May 2018.

16

AMIRI HANZAEI AMIN ، SEYEDIN SANAZ ، AHADI SARKANI S.M., "Multi-layer kullback-leibler based Complex NMF with LPC error Clustering for Blind Source Separation,", 7th International Conference on Computer and Knowledge Engineering, Oct 2017.

17

SAFARI RAZIEH ، AHADI SARKANI S.M. ، SEYEDIN SANAZ, "Modular Dynamic Deep Denoising Autoencoder for Speech Enhancement,", 7th International Conference on Computer and Knowledge Engineering 2017, Oct 2017.

18

REZAEI MEHDI ، SEYEDIN SANAZ, "Robust image watermarking in wavelet domain using SVR,", 2nd International Conference on Signal Processing and Intelligent Systems, Dec 2016.

19

Nastaran Borjian ، Ehsanollah Kabir ، SEYEDIN SANAZ ، Ellipse Masehian, "Music retrieval using a Gaussian Mixture Model,", ISAV2014, Dec 2014.

20

SEYEDIN SANAZ ، Ramin Pichevar ، Jean Rouat, "Discriminative sparse-based feature extraction and dictionary learning for sound classification applications,", 11th Int. Conf. on Information Science, Signal Processing and their Applications (ISSPA), Jul 2012.

21

SEYEDIN SANAZ ، AHADI SARKANI S.M., "Robust MVDR-based feature extraction for speech recognition,", 7th Int. Conf. on Information, Communications and Signal Processing, ICICS, Dec 2009.

22

SEYEDIN SANAZ ، AHADI SARKANI S.M., "Feature extraction based on DCT and MVDR spectral estimation for robust speech recognition,", 9th International Conference on Signal Processing, Oct 2008.

23

SEYEDIN SANAZ ، Shahriar B. Shokouhi, "A New Robust Color Coding Technique for Solving the Correspondence Problem and 3D Reconstruction in Structured Light Systems,", 2nd International Conference on Information & Communication Technologies, Apr 2006.

1

N. Borjian, E. Kabir, S. Seyedin, E. Masihi, "Music retrieval using Gaussian-Markov classifier", 2014.

2

S Seyedin, R. Pichevar, J. Rouat, "Discriminative sparse-based feature extraction and dictionary learning for sound classification applications", 2012.

3

S. Seyedin, S. M. Ahadi, "Robust MVDR-based feature extraction for speech recognition", 2009.

4

S. Seyedin, S. M. Ahadi, "Feature extraction based on DCT and MVDR spectral estimation for robust speech recognition", 2008.

5

S. Seyedin, S. B. Shokouhi, "A new robust color coding technique for solving the correspondence problem and 3D reconstruction in structured light systems", 2006.

Awards & Honors

#

title

Date

1

First rank PhD Graduate, Electrical Engineering Department, Amirkabir University of Technology

Oct. 2010

2

First rank M.S. Graduate, Electrical Engineering Department,University of Science and Technology

Sep. 2005

3

First rank B.S. Graduate, Electrical Engineering Department, Amirkabir University of Technology

Dec. 2001

Professional Memberships

#

Professional memberships

Explanations

1

IEEE Senior Member

Taught Courses

#

Course title

Description

Headlines

Date

1

Introduction to Machine Learning

4051

2

Machine Learning

4042

3

Logic Circuits

4042

4

Introduction to Machine Learning

4041

5

Digital Signal Processing

4041

6

Logic Circuits

4032

7

Machine Learning

4032