Search Results for author:
Found 39 papers, 12 papers with code
IIE’s Neural Machine Translation Systems for WMT20
In this paper we introduce the systems IIE submitted for the WMT20 shared task on German-French news translation.
Normalising Flow-based Differentiable Particle Filters
Recently, there has been a surge of interest in incorporating neural networks into particle filters, e. g. differentiable particle filters, to perform joint sequential state estimation and model learning for non-linear non-Gaussian state-space models in complex environments.
StreamVC: Real-Time Low-Latency Voice Conversion
We present StreamVC, a streaming voice conversion solution that preserves the content and prosody of any source speech while matching the voice timbre from any target speech.
Learning Differentiable Particle Filter on the Fly
Differentiable particle filters are an emerging class of sequential Bayesian inference techniques that use neural networks to construct components in state space models.
Guided Speech Enhancement Network
Multi-microphone speech enhancement problem is often decomposed into two decoupled steps: a beamformer that provides spatial filtering and a single-channel speech enhancement model that cleans up the beamformer output.
Differentiable Bootstrap Particle Filters for Regime-Switching Models
Differentiable particle filters are an emerging class of particle filtering methods that use neural networks to construct and learn parametric state-space models.
An overview of differentiable particle filters for data-adaptive sequential Bayesian inference
Due to the expressiveness of neural networks, differentiable particle filters are a promising computational tool for performing inference on sequential data in complex, high-dimensional tasks, such as vision-based robot localisation.
Particle Flow Gaussian Sum Particle Filter
In this paper, we use bank of PFGPF filters to construct a Particle flow Gaussian sum particle filter (PFGSPF), which approximates the predictive and posterior as Gaussian mixture model.
FADO: Feedback-Aware Double COntrolling Network for Emotional Support Conversation
The core module in FADO consists of a dual-level feedback strategy selector and a double control reader.
Psychology-guided Controllable Story Generation
Inspired by psychology theories, we introduce global psychological state chains, which include the needs and emotions of the protagonists, to help a story generation system create more controllable and well-planned stories.
Particle Flow Gaussian Particle Filter
State estimation in non-linear models is performed by tracking the posterior distribution recursively.
Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection
Out-of-distribution (OOD) detection has recently received much attention from the machine learning community due to its importance in deploying machine learning models in real-world applications.
Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversation
Emotional support conversation aims at reducing the emotional distress of the help-seeker, which is a new and challenging task.
Conditional Measurement Density Estimation in Sequential Monte Carlo via Normalizing Flow
Tuning of measurement models is challenging in real-world applications of sequential Monte Carlo methods.
Real time spectrogram inversion on mobile phone
We present two methods of real time magnitude spectrogram inversion: streaming Griffin Lim(GL) and streaming MelGAN.
CLSEG: Contrastive Learning of Story Ending Generation
To address these two issues, we propose a novel Contrastive Learning framework for Story Ending Generation (CLSEG), which has two steps: multi-aspect sampling and story-specific contrastive learning.
Boosting Independent Component Analysis
Independent component analysis is intended to recover the mutually independent components from their linear mixtures.
Second-order Approximation of Minimum Discrimination Information in Independent Component Analysis
Independent Component Analysis (ICA) is intended to recover the mutually independent sources from their linear mixtures, and F astICA is one of the most successful ICA algorithms.
HumBugDB: A Large-scale Acoustic Mosquito Dataset
Our extensive dataset is both challenging to machine learning researchers focusing on acoustic identification, and critical to entomologists, geo-spatial modellers and other domain experts to understand mosquito behaviour, model their distribution, and manage the threat they pose to humans.
Folded Hamiltonian Monte Carlo for Bayesian Generative Adversarial Networks
Generative Adversarial Networks (GANs) can learn complex distributions over images, audio, and data that are difficult to model.
Modifications of FastICA in Convolutive Blind Source Separation
Convolutive blind source separation (BSS) is intended to recover the unknown components from their convolutive mixtures.
Differentiable Particle Filters through Conditional Normalizing Flow
Differentiable particle filters provide a flexible mechanism to adaptively train dynamic and measurement models by learning from observed data.
Towards Unsupervised Sketch-based Image Retrieval
The practical value of existing supervised sketch-based image retrieval (SBIR) algorithms is largely limited by the requirement for intensive data collection and labeling.
Boosting in Univariate Nonparametric Maximum Likelihood Estimation
Nonparametric maximum likelihood estimation is intended to infer the unknown density distribution while making as few assumptions as possible.
End-To-End Semi-supervised Learning for Differentiable Particle Filters
Recent advances in incorporating neural networks into particle filters provide the desired flexibility to apply particle filters in large-scale real-world applications.
MicAugment: One-shot Microphone Style Transfer
A crucial aspect for the successful deployment of audio-based models "in-the-wild" is the robustness to the transformations introduced by heterogeneous acquisition conditions.
SEANet: A Multi-modal Speech Enhancement Network
We explore the possibility of leveraging accelerometer data to perform speech enhancement in very noisy conditions.
Imitation Learning with Sinkhorn Distances
In this paper, we present tractable solutions by formulating imitation learning as minimization of the Sinkhorn distance between occupancy measures.
Learning to Denoise Historical Music
We propose an audio-to-audio neural network model that learns to denoise old music recordings.
Augmented Sliced Wasserstein Distances
While theoretically appealing, the application of the Wasserstein distance to large-scale machine learning problems has been hampered by its prohibitive computational cost.
From Here to There: Video Inbetweening Using Direct 3D Convolutions
We first obtain a latent video representation using a stochastic fusion mechanism that learns how to incorporate information from the start and end frames.
An Empirical Study of Generative Models with Encoders
Generative adversarial networks (GANs) are capable of producing high quality image samples.
BCCNet: Bayesian classifier combination neural network
Machine learning research for developing countries can demonstrate clear sustainable impact by delivering actionable and timely information to in-country government organisations (GOs) and NGOs in response to their critical information requirements.
Cost-sensitive detection with variational autoencoders for environmental acoustic sensing
Environmental acoustic sensing involves the retrieval and processing of audio signals to better understand our surroundings.
Mosquito detection with low-cost smartphones: data acquisition for malaria research
Mosquitoes are a major vector for malaria, causing hundreds of thousands of deaths in the developing world each year.
Microwave breast cancer detection using Empirical Mode Decomposition features
One of the most widely used feature extraction method is principle component analysis (PCA).
Defuzzify firstly or finally: Dose it matter in fuzzy DEMATEL under uncertain environment?
The results of defuzzification at the first step are not coincide with the results of defuzzification at the final step. It seems that the alternative is to defuzzification in the final step in fuzzy DEMATEL.
A brief network analysis of Artificial Intelligence publication
In this paper, we present an illustration to the history of Artificial Intelligence(AI) with a statistical analysis of publish since 1940.
Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets
We propose a working set based approximate subgradient descent algorithm to minimize the margin-sensitive hinge loss arising from the soft constraints in max-margin learning frameworks, such as the structured SVM.
