1 code implementation • 5 Feb 2022 • Mohammad Khalooei, Mohammad Mehdi Homayounpour, Maryam Amirmazlaghani
This paper introduces a novel framework (Layer Sustainability Analysis (LSA)) for the analysis of layer vulnerability in an arbitrary neural network in the scenario of adversarial attacks.
1 code implementation • 5 Sep 2021 • Amir Mohammad Rostami, Mohammad Mehdi Homayounpour, Ahmad Nickabadi
Many endeavors have sought to develop countermeasure techniques as enhancements on Automatic Speaker Verification (ASV) systems, in order to make them more robust against spoof attacks.
Ranked #1 on Spoof Detection on ASVspoof 2019 - LA
no code implementations • 7 Jan 2017 • Mohaddeseh Bastan, Shahram Khadivi, Mohammad Mehdi Homayounpour
This new loss function yields a total of 1. 87 point improvements in terms of BLEU score in the translation quality.
no code implementations • 5 Oct 2016 • Mahdi Khademian, Mohammad Mehdi Homayounpour
The proposed method of the IBM team, consist of an intermediate speech separation and then a single-talker speech recognition.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 9 Mar 2015 • Mahdi Khademian, Mohammad Mehdi Homayounpour
This paper investigates the effectiveness of factorial speech processing models in noise-robust automatic speech recognition tasks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 14 Nov 2014 • Mohammad Ali Keyvanrad, Mohammad Mehdi Homayounpour
Deep Belief Networks (DBNs) are deep architectures that use stack of Restricted Boltzmann Machines (RBM) to create a powerful generative model using training data.
no code implementations • 14 Aug 2014 • Mohammad Ali Keyvanrad, Mohammad Mehdi Homayounpour
Nowadays, this is very popular to use the deep architectures in machine learning.