Search Results for author:
Found 7 papers, 2 papers with code
Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework
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.
Efficient Attention Branch Network with Combined Loss Function for Automatic Speaker Verification Spoof Detection
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
Neural Machine Translation on Scarce-Resource Condition: A case-study on Persian-English
This new loss function yields a total of 1. 87 point improvements in terms of BLEU score in the translation quality.
Monaural Multi-Talker Speech Recognition using Factorial Speech Processing Models
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
Modeling State-Conditional Observation Distribution using Weighted Stereo Samples for Factorial Speech Processing Models
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
Deep Belief Network Training Improvement Using Elite Samples Minimizing Free Energy
Deep Belief Networks (DBNs) are deep architectures that use stack of Restricted Boltzmann Machines (RBM) to create a powerful generative model using training data.
A brief survey on deep belief networks and introducing a new object oriented toolbox (DeeBNet)
Nowadays, this is very popular to use the deep architectures in machine learning.
