相关论文: A vector quantized masked autoencoder for audiovis…

Video understanding relies on perceiving the global content and modeling its internal connections (e.g., causality, movement, and spatio-temporal correspondence). To learn these interactions, we apply a mask-then-predict pre-training task…

In this paper, we are interested in audio-visual speech separation given a single-channel audio recording as well as visual information (lips movements) associated with each speaker. We propose an unsupervised technique based on…

Although deep generative models have gained a lot of attention, most of the existing works are designed for unimodal generation. In this paper, we explore a new method for unconditional image-text pair generation. We design Multimodal…

The hematology analytics used for detection and classification of small blood components is a significant challenge. In particular, when objects exists as small pixel-sized entities in a large context of similar objects. Deep learning…

In this paper, we propose a new methodology for emotional speech recognition using visual deep neural network models. We employ the transfer learning capabilities of the pre-trained computer vision deep models to have a mandate for the…

Talking face generation is a novel and challenging generation task, aiming at synthesizing a vivid speaking-face video given a specific audio. To fulfill emotion-controllable talking face generation, current methods need to overcome two…

Learning transferable representations from unlabeled time series is crucial for improving performance in data-scarce classification. Existing self-supervised methods often operate at the point level and rely on unidirectional encoding,…

Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of…

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

Masked Autoencoders (MAEs) trained on audio spectrogram patches have emerged as a prominent approach for learning self-supervised audio representations. While several recent papers have evaluated key aspects of training MAEs on audio data,…

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based autoencoders have shown great potential in detecting anomalies in medical images. However, especially…

Although speech is a simple and effective way for humans to communicate with the outside world, a more realistic speech interaction contains multimodal information, e.g., vision, text. How to design a unified framework to integrate…

We describe our submitted system for the ZeroSpeech Challenge 2019. The current challenge theme addresses the difficulty of constructing a speech synthesizer without any text or phonetic labels and requires a system that can (1) discover…

Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However,…

Decoding speech from non-invasive brain signals, such as electroencephalography (EEG), has the potential to advance brain-computer interfaces (BCIs), with applications in silent communication and assistive technologies for individuals with…

Self-supervised pre-training for images without labels has recently achieved promising performance in image classification. The success of transformer-based methods, ViT and MAE, draws the community's attention to the design of backbone…

Learning aligned multimodal embeddings from weakly paired, label-free corpora is challenging: pipelines often provide only pre-extracted features, clips contain multiple events, and spurious co-occurrences. We propose HSC-MAE (Hierarchical…

In this paper we introduce a recurrent neural network (RNN) based variational autoencoder (VAE) model with a new constrained loss function that can generate more meaningful electroencephalography (EEG) features from raw EEG features to…

Recently, various studies have been directed towards exploring dense passage retrieval techniques employing pre-trained language models, among which the masked auto-encoder (MAE) pre-training architecture has emerged as the most promising.…

Inspired by the success of deep neural networks (DNNs) in speech processing, this paper presents Deep Vocoder, a direct end-to-end low bit rate speech compression method with deep autoencoder (DAE). In Deep Vocoder, DAE is used for…