Related papers: Semantic-VAE: Semantic-Alignment Latent Representa…

Wav2vec-C introduces a novel representation learning technique combining elements from wav2vec 2.0 and VQ-VAE. Our model learns to reproduce quantized representations from partially masked speech encoding using a contrastive loss in a way…

Semantic communication systems introduce a new paradigm in wireless communications, focusing on transmitting the intended meaning rather than ensuring strict bit-level accuracy. These systems often rely on Deep Neural Networks (DNNs) to…

Automatic speaker verification (ASV) systems are highly vulnerable to presentation attacks, also called spoofing attacks. Replay is among the simplest attacks to mount - yet difficult to detect reliably. The generalization failure of…

Learning compact and meaningful latent space representations has been shown to be very useful in generative modeling tasks for visual data. One particular example is applying Vector Quantization (VQ) in variational autoencoders (VQ-VAEs,…

Word embedding, a high-dimensional (HD) numerical representation of words generated by machine learning models, has been used for different natural language processing tasks, e.g., translation between two languages. Recently, there has been…

Vision-Language Model (VLM) is an important component to enable robust robot manipulation. Yet, using it to translate human instructions into an action-resolvable intermediate representation often needs a tradeoff between…

With the continued proliferation of Large Language Model (LLM) based chatbots, there is a growing demand for generating responses that are not only linguistically fluent but also consistently aligned with persona-specific traits in…

Representation disentanglement is an important goal of representation learning that benefits various downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been developed. However,…

Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…

Recent advancements in video super-resolution (VSR) models have demonstrated impressive results in enhancing low-resolution videos. However, due to limitations in adequately controlling the generation process, achieving high fidelity…

In recent years, applying Deep Learning (DL) techniques emerged as a common practice in the communication system, demonstrating promising results. The present paper proposes a new Convolutional Neural Network (CNN) based Variational…

Deep speaker embedding has achieved state-of-the-art performance in speaker recognition. A potential problem of these embedded vectors (called `x-vectors') are not Gaussian, causing performance degradation with the famous PLDA back-end…

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space…

Although the semantic communications have exhibited satisfactory performance in a large number of tasks, the impact of semantic noise and the robustness of the systems have not been well investigated. Semantic noise is a particular kind of…

Variational autoencoder-based voice conversion (VAE-VC) has the advantage of requiring only pairs of speeches and speaker labels for training. Unlike the majority of the research in VAE-VC which focuses on utilizing auxiliary losses or…

Variational autoencoders (VAEs) are among leading approaches to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled representations are sought within its single continuous latent…

A variational autoencoder (VAE) is a probabilistic machine learning framework for posterior inference that projects an input set of high-dimensional data to a lower-dimensional, latent space. The latent space learned with a VAE offers…

This paper presents an accurate phoneme alignment model that aims for speech analysis and video content creation. We propose a variational autoencoder (VAE)-based alignment model in which a probable path is searched using encoded acoustic…

In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image…

Current two-stage TTS framework typically integrates an acoustic model with a vocoder -- the acoustic model predicts a low resolution intermediate representation such as Mel-spectrum while the vocoder generates waveform from the…