Related papers: Salient Speech Representations Based on Cloned Net…

We propose to implement speech enhancement by the regeneration of clean speech from a salient representation extracted from the noisy signal. The network that extracts salient features is trained using a set of weight-sharing clones of the…

Salient object detection has seen remarkable progress driven by deep learning techniques. However, most of deep learning based salient object detection methods are black-box in nature and lacking in interpretability. This paper proposes the…

Various sources have reported the WaveNet deep learning architecture being able to generate high-quality speech, but to our knowledge there haven't been studies on the interpretation or visualization of trained WaveNets. This study…

While a lot of work has been done in understanding representations learned within deep NLP models and what knowledge they capture, little attention has been paid towards individual neurons. We present a technique called as Linguistic…

This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. The model is fully probabilistic and autoregressive, with the predictive distribution for each audio sample conditioned on all previous ones;…

Complex networks in natural, social, and technological systems generically exhibit an abundance of rich information. Extracting meaningful structural features from data is one of the most challenging tasks in network theory. Many methods…

In this paper, we propose a novel deep neural network framework embedded with low-level features (LCNN) for salient object detection in complex images. We utilise the advantage of convolutional neural networks to automatically learn the…

Voice cloning is a highly desired feature for personalized speech interfaces. Neural network based speech synthesis has been shown to generate high quality speech for a large number of speakers. In this paper, we introduce a neural voice…

State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with limited annotated data. To overcome this challenge, we design a data-oriented approach that first…

Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…

Salient segmentation aims to segment out attention-grabbing regions, a critical yet challenging task and the foundation of many high-level computer vision applications. It requires semantic-aware grouping of pixels into salient regions and…

Recent generative data augmentation methods conditioned on both image and text prompts struggle to balance between fidelity and diversity, as it is challenging to preserve essential image details while aligning with varied text prompts.…

Network interpretation as an effort to reveal the features learned by a network remains largely visualization-based. In this paper, our goal is to tackle semantic network interpretation at both filter and decision level. For filter-level…

Human speakers encode information into raw speech which is then decoded by the listeners. This complex relationship between encoding (production) and decoding (perception) is often modeled separately. Here, we test how encoding and decoding…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Semantic communication, leveraging advanced deep learning techniques, emerges as a new paradigm that meets the requirements of next-generation wireless networks. However, current semantic communication systems, which employ neural coding…

We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to…

Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in…

Finding semantic correspondences is a challenging problem. With the breakthrough of CNNs stronger features are available for tasks like classification but not specifically for the requirements of semantic matching. In the following we…

Deep neural networks are complex and opaque. As they enter application in a variety of important and safety critical domains, users seek methods to explain their output predictions. We develop an approach to explaining deep neural networks…