Index

Muhammad Ali Tahir
Assistant Professor
Department of Computing

School of Electrical Engineering and Computer Science (SEECS)
National University of Sciences and Technology (NUST)
NUST Campus H-12, Islamabad
Tel: 05190852163
Email: ali.tahir@seecs.edu.pk
Web: http://speech.seecs.nust.edu.pk/index.html

Specialization:
Automatic Speech Recognition, Pattern Recognition, Image Processing

Education:
Ph.D. - Computer Science / Automatic Speech Recognition - RWTH Aachen University - Germany - 2015

Dr. Muhammad Ali Tahir has completed his Ph.D. in Automatic speech recognition from RWTH Aachen University. During his 11 year stay in Germany he has worked on different EU-funded projects related to speech recognition, primarily aiming to bridge the language divide in a multilingual Europe. During his time at NUST he has been collaborating with local industry to create Urdu voice based solutions for conversational agents and vehicle navigation. He has also launched an Urdu website UrduAsr which is being used by thousands of people for Urdu voice based typing.


Memberships: HEC Patent Evaluation Committee, Association for Computing Machinery, Pakistan Engineering Council
Journals Reviewer: Elsevier Computer Speech and Language, IEEE Journal of Biomedical and Health Informatics


Research Experience

Research Associate (full-time) , RWTH Aachen University

October 2011 - December 2015

Details: Worked on various European-funded projects in close cooperation with other academic and industrial partners, primarily in the domain of automatic speech recognition and neural networks * QUAERO: European research and development program with the goal of developing multimedia and multilingual indexing and management tools for professional and general public applications * Translectures: an EU-funded project to develop innovative, cost-effective tools for the automatic transcription and translation of online educational videos. * EU-Bridge: a multisite-project designed to build and promote bridges across the language divide. With 24 official languages in Europe language barriers represent a considerable challenge to communication in Europe.
Research consultant , TPL Trakker Ltd. Karachi

January 2017 - July 2017

Details: Speech Based Interaction for Vehicle Navigation System
PI , NRTC

July 2019 - December 2019

Details: Development of Urdu speech recognition system for surveillance
Journal

(1.) A. Rauf , Z. Wang, H. Sajid, M. A. Tahir , "Secure Route-Obfuscation Mechanism with Information-Theoretic Security for Internet of Things", Sensors - special issue Internet of Things, Big Data and Smart Systems, Vol. 20 , No. 15, Jul, 2020. IF: 3.2
(2.) A. Pervaiz , F. Hussain, H. Israr, M. A. Tahir, F. R. Raja, N. K. Baloch, F. Ishmanov, Y. B. Zikria , "Incorporating noise robustness in speech command recognition by noise augmentation of training data", Sensors - special issue VOICE Sensors with Deep Learning, Vol. 20 , No. 8, Apr, 2020. IF: 3.0
(3.) M. A. Tahir , H. Huang, A. Zeyer, R. Schlüter, H. Ney , "Training of Reduced-Rank Linear Transformations for Multi-layer Polynomial Acoustic Features for Speech Recognition", Elsevier Speech Communication, ISSN 0167-6393, Vol. 110 , No. 1, PP. 56-63, Jul, 2019. IF: 1.8

Conference

(1.) A. Rauf , Z. Wang, H. Sajid, M. A. Tahir , "Efficient Distributed Key Agreement for Edge Devices in the Internet of Things with Information-Theoretic Security", Proceedings of the 7th International Cryptology and Information Security Conference, Jun, 2020, Online , Malaysia.
(2.) F. Zafar , S. Raza, M. U. Khalid, M. A. Tahir , "Predictive Analytics in Healthcare for Diabetes Prediction", Proceedings of the 9th International Conference on Biomedical Engineering and Technology, Mar, 2019, Tokyo , Japan.
(3.) Y. Ghazi , Z. Anwar, R. Mumtaz, S. Saleem, A. Tahir , "A Supervised Machine Learning Based Approach for Automatically Extracting High-Level Threat Intelligence from Unstructured Sources", Proceedings of the International Conference on Frontiers of Information Technology, Dec, 2018, Islamabad , Pakistan.
(4.) W. Nawaz , S. Ahmed, M. A. Tahir, H. A. Khan , "Classification Of Breast Cancer Histology Images Using ALEXNET", Proceedings of the International Conference on Image Analysis and Recognition, Jun, 2018, Póvoa de Varzim , Portugal.
(5.) M. A. B. Shaik , Z. Tüske, M. A. Tahir, M. Nußbaum-Thom, R. Schlüter, and H. Ney , "Improvements in RWTH LVCSR evaluation systems for Polish, Portuguese, English, Urdu, and Arabic", Proceedings of the Interspeech, Sep, 2015, Dresden , Germany.
(6.) M. A. Tahir , S. Wiesler, R. Schlueter, H. Ney , "Investigation of Mixture Splitting Concept for Training Linear Bottlenecks of Deep Neural Network Acoustic Models", Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr, 2015, Brisbane , Australia.
(7.) Z. Tüske , M. A. Tahir, R. Schlüter, H. Ney , "Integrating Gaussian Mixtures into Deep Neural Networks: Softmax Layer with Hidden Variables", Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr, 2015, Brisbane , Australia.
(8.) M. A. B. Shaik , Z. Tüske, M. A. Tahir, M. Nußbaum-Thom, R. Schlüter, H. Ney , "RWTH LVCSR Systems for Quaero and EU-Bridge: German, Polish, Spanish and Portuguese", Proceedings of the Interspeech, Sep, 2014, , Singapore.
(9.) M. A. Tahir , H. Huang, R. Schlueter, H. Ney, L. t. Bosch, B. Cranen, L. Boves , "Training Log-Linear Acoustic Models in Higher-Order Polynomial Feature Space for Speech Recognition", Proceedings of the Interspeech, Aug, 2013, Lyon , France.
(10.) M. A. Tahir , M. Nussbaum, R. Schlueter, H. Ney , "Simultaneous Discriminative Training and Mixture Splitting of HMMs for Speech Recognition", Proceedings of the Interspeech, Sep, 2012, Portland, OR , United States.
(11.) M. A. Tahir , R, Schlueter, H. Ney , "Discriminative Splitting of Gaussian/Log-Linear Mixture HMMs for Speech Recognition", Proceedings of the IEEE Automatic Speech Recognition and Understanding, Dec, 2011, Waikaloa, HI , United States.
(12.) M. A. Tahir , R, Schlueter, H. Ney , "Log-linear Optimization of Second-order Polynomial Features with Subsequent Dimension Reduction for Speech Recognition", Proceedings of the Interspeech, Aug, 2011, Florence , Italy.
(13.) M. A. Tahir , G. Heigold, C. Plahl, R. Schlueter, H. Ney , "Log-Linear Framework for Linear Feature Transformations in Speech Recognition", Proceedings of the IEEE Automatic Speech Recognition and Understanding, Dec, 2009, Merano , Italy.
(14.) R. Hafiz , M. A. Tahir, O. Arshad, S. Khan , "An optimized hardware accelerator for real time registration of aerial video imagery and its applications", Proceedings of the Third International Conference on Image and Graphics, Dec, 2004, Hong Kong , China.
(15.) M. A. Tahir , A. Munawar, I. A. Taj , "Efficient use of multipliers in microprocessor implementation of Hamming distance for binary sequence correlation", Proceedings of the International Networking and Communication Conference, Jun, 2004, Lahore , Pakistan.
(16.) R. Hafiz , M. A. Tahir, O. Arshad, S. Khan , "Hardware design for registration of aerial video imagery", Proceedings of the 8th International Multitopic Conference, Jan, 2004, Lahore , Pakistan.

Assistant Professor , SEECS, NUST
February 2016 - Present

Details: Courses: CS 330 operating systems, CS 251 Design and Analysis of Algorithms

Visiting Lecturer , Foundation University
April 2004 - August 2004

Details: Course: Digital Image Processing

Teaching Assistant , Center for Advanced Studies in Engineering (CASE)
September 2004 - January 2005

Details: Course: Digital Image Processing


Design Engineer , Center for Advanced Research in Engineering
August 2003 - January 2005

Details: Worked on several indigenous technology development projects involving GIS, digital communication and image processing.