相关论文: Deep Variational Generative Models for Audio-visua…

Deep Learning based methods have emerged as the indisputable leaders for virtually all image restoration tasks. Especially in the domain of microscopy images, various content-aware image restoration (CARE) approaches are now used to improve…

State-of-the-art Variational Auto-Encoders (VAEs) for learning disentangled latent representations give impressive results in discovering features like pitch, pause duration, and accent in speech data, leading to highly controllable…

Self-supervised speech pre-training methods have developed rapidly in recent years, which show to be very effective for many near-field single-channel speech tasks. However, far-field multichannel speech processing is suffering from the…

Tools to generate high quality synthetic speech signal that is perceptually indistinguishable from speech recorded from human speakers are easily available. Several approaches have been proposed for detecting synthetic speech. Many of these…

Linking neural representations to linguistic factors is crucial in order to build and analyze NLP models interpretable by humans. Among these factors, syntactic roles (e.g. subjects, direct objects,$\dots$) and their realizations are…

Semi-supervised learning is attracting increasing attention due to the fact that datasets of many domains lack enough labeled data. Variational Auto-Encoder (VAE), in particular, has demonstrated the benefits of semi-supervised learning.…

As deep neural networks become more adept at traditional tasks, many of the most exciting new challenges concern multimodality---observations that combine diverse types, such as image and text. In this paper, we introduce a family of…

The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling…

Learning interpretable and disentangled representations of data is a key topic in machine learning research. Variational Autoencoder (VAE) is a scalable method for learning directed latent variable models of complex data. It employs a clear…

Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we…

Deep generative neural networks, such as Variational AutoEncoders (VAEs), offer an opportunity to better understand and control language models from the perspective of sentence-level latent spaces. To combine the controllability of VAE…

Despite the rapid advance of automatic speech recognition (ASR) technologies, accurate recognition of cocktail party speech characterised by the interference from overlapping speakers, background noise and room reverberation remains a…

Training deep neural networks on well-understood dependencies in speech data can provide new insights into how they learn internal representations. This paper argues that acquisition of speech can be modeled as a dependency between random…

Past work on story generation has demonstrated the usefulness of conditioning on a generation plan to generate coherent stories. However, these approaches have used heuristics or off-the-shelf models to first tag training stories with the…

The objective of this work is to extract target speaker's voice from a mixture of voices using visual cues. Existing works on audio-visual speech separation have demonstrated their performance with promising intelligibility, but maintaining…

In this paper, we propose a multi-channel speech source separation with a deep neural network (DNN) which is trained under the condition that no clean signal is available. As an alternative to a clean signal, the proposed method adopts an…

Separating a song into vocal and accompaniment components is an active research topic, and recent years witnessed an increased performance from supervised training using deep learning techniques. We propose to apply the visual information…

Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution. Recent advances have…

Deep neural network models trained on large labeled datasets are the state-of-the-art in a large variety of computer vision tasks. In many applications, however, labeled data is expensive to obtain or requires a time consuming manual…

Disentangled representation learning aims to represent the underlying generative factors of a dataset in a latent representation independently of one another. In our work, we propose a discrete variational autoencoder (VAE) based model…