• Evaluation of Handwritten Urdu Text by Integration of MNIST Dataset Learning Experience 

      Bin Ahmed, Saad; Hameed, Ibrahim A.; Naz, Saeeda; Imran Razzak, Muhammad; Yusof, Rubiyah (Journal article; Peer reviewed, 2019)
      The similar nature of patterns may enhance the learning if the experience they attained during training is utilized to achieve maximum accuracy. This paper presents a novel way to exploit the transfer learning experience ...
    • Regularized Urdu Speech Recognition with Semi-Supervised Deep Learning 

      Ali Humayun, Mohammad; Hameed, Ibrahim A.; Muslim Shah, Syed; Hassan Khan, Sohaib; Zafar, Irfan; Bin Ahmed, Saad; Shuja, Junaid (Journal article; Peer reviewed, 2019)
      Automatic Speech Recognition, (ASR) has achieved the best results for English, with end-to-end neural network based supervised models. These supervised models need huge amounts of labeled speech data for good generalization, ...