Search Results for author:
Found 21 papers, 8 papers with code
PI-RADS v2 Compliant Automated Segmentation of Prostate Zones Using co-training Motivated Multi-task Dual-Path CNN
Further, the representations from different branches act complementary to each other at the second stage of training, where they are fine-tuned through an unsupervised loss.
Improving Voice Conversion for Dissimilar Speakers Using Perceptual Losses
The rising trend of using voice as a means of interacting with smart devices has sparked worries over the protection of users' privacy and data security.
Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion
Speech anonymisation prevents misuse of spoken data by removing any personal identifier while preserving at least linguistic content.
StarGAN-VC++: Towards Emotion Preserving Voice Conversion Using Deep Embeddings
In this paper, we show that StarGANv2-VC fails to disentangle the speaker and emotion representations, pertinent to preserve emotion.
Learning Continuous Rotation Canonicalization with Radial Beam Sampling
The inductive biases inherent to convolutional neural networks allow for translation equivariance through kernels acting parallely to the horizontal and vertical axes of the pixel grid.
Visualizing Deep Neural Networks with Topographic Activation Maps
Machine Learning with Deep Neural Networks (DNNs) has become a successful tool in solving tasks across various fields of application.
Differentiable Generalised Predictive Coding
The model suggested here optimises hierarchical and dynamical predictions of latent states.
PredProp: Bidirectional Stochastic Optimization with Precision Weighted Predictive Coding
We present PredProp, a method for optimization of weights and states in predictive coding networks (PCNs) based on the precision of propagated errors and neural activity.
Predictive coding, precision and natural gradients
Here we focus on the related, but still largely under-explored connection between precision weighting in predictive coding networks and the Natural Gradient Descent algorithm for deep neural networks.
Evaluation of deep lift pose models for 3D rodent pose estimation based on geometrically triangulated data
Here we propose the usage of lift-pose models that allow for robust 3D pose estimation of freely moving rodents from a single view camera view.
Uncertainty-Aware Temporal Self-Learning (UATS): Semi-Supervised Learning for Segmentation of Prostate Zones and Beyond
Various convolutional neural network (CNN) based concepts have been introduced for the prostate's automatic segmentation and its coarse subdivision into transition zone (TZ) and peripheral zone (PZ).
Exploration of Interpretability Techniques for Deep COVID-19 Classification using Chest X-ray Images
The outbreak of COVID-19 has shocked the entire world with its fairly rapid spread and has challenged different sectors.
Gradient-Adjusted Neuron Activation Profiles for Comprehensive Introspection of Convolutional Speech Recognition Models
This includes different ways of visualizing features and clustering of GradNAPs to compare embeddings of different groups of inputs in any layer of a given network.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Visualizing Deep Neural Networks for Speech Recognition with Learned Topographic Filter Maps
The uninformative ordering of artificial neurons in Deep Neural Networks complicates visualizing activations in deeper layers.
Window-Based Neural Tagging for Shallow Discourse Argument Labeling
This paper describes a novel approach for the task of end-to-end argument labeling in shallow discourse parsing.
PredNet and Predictive Coding: A Critical Review
We fill in the gap by evaluating PredNet both as an implementation of the predictive coding theory and as a self-supervised video prediction model using a challenging video action classification dataset.
Introspection for convolutional automatic speech recognition
Our method integrates information from many data examples through local introspection techniques for Convolutional Neural Networks (CNNs).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Hybrid Active Inference
To establish this, a machine learning part learns to integrate into human cognition by explaining away multi-modal sensory measurements from the environment and physiology simultaneously with the brain signal.
Transfer Learning for Speech Recognition on a Budget
End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources.
Deep Feature Learning for EEG Recordings
We introduce and compare several strategies for learning discriminative features from electroencephalography (EEG) recordings using deep learning techniques.
Using Convolutional Neural Networks to Recognize Rhythm Stimuli from Electroencephalography Recordings
Electroencephalography (EEG) recordings of rhythm perception might contain enough information to distinguish different rhythm types/genres or even identify the rhythms themselves.
