Related papers: Separable Temporal Convolution plus Temporally Poo…

Multi-head self-attention forms the core of Transformer networks. However, their quadratically growing complexity with respect to the input sequence length impedes their deployment on resource-constrained edge devices. We address this…

Weakly-Supervised Semantic Segmentation (WSSS) methods with image-level labels generally train a classification network to generate the Class Activation Maps (CAMs) as the initial coarse segmentation labels. However, current WSSS methods…

Spoken keyword spotting (KWS) is the task of identifying a keyword in an audio stream and is widely used in smart devices at the edge in order to activate voice assistants and perform hands-free tasks. The task is daunting as there is a…

Deep learning-based medical image segmentation technology aims at automatic recognizing and annotating objects on the medical image. Non-local attention and feature learning by multi-scale methods are widely used to model network, which…

Keyword spotting (KWS) is one of the speech recognition tasks most sensitive to the quality of the feature representation. However, the research on KWS has traditionally focused on new model topologies, putting little emphasis on other…

In recent years, there has been a growing interest in designing small-footprint yet effective Connectionist Temporal Classification based keyword spotting (CTC-KWS) systems. They are typically deployed on low-resource computing platforms,…

A keyword spotting (KWS) system determines the existence of, usually predefined, keyword in a continuous speech stream. This paper presents a query-by-example on-device KWS system which is user-specific. The proposed system consists of two…

Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the…

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

This paper describes the system developed by the NPU team for the 2020 personalized voice trigger challenge. Our submitted system consists of two independently trained subsystems: a small footprint keyword spotting (KWS) system and a…

Remaining useful life prediction plays a crucial role in the health management of industrial systems. Given the increasing complexity of systems, data-driven predictive models have attracted significant research interest. Upon reviewing the…

Spatiotemporal predictive learning aims to generate future frames by learning from historical frames. In this paper, we investigate existing methods and present a general framework of spatiotemporal predictive learning, in which the spatial…

Speech recognition is a sequence prediction problem. Besides employing various deep learning approaches for framelevel classification, sequence-level discriminative training has been proved to be indispensable to achieve the…

This paper proposes speaker-adaptive neural vocoders for parametric text-to-speech (TTS) systems. Recently proposed WaveNet-based neural vocoding systems successfully generate a time sequence of speech signal with an autoregressive…

Recently, Convolutional Neural Network (CNN) and Long short-term memory (LSTM) based models have been introduced to deep learning-based target speaker separation. In this paper, we propose an Attention-based neural network (Atss-Net) in the…

LWM-Temporal is a new member of the Large Wireless Models (LWM) family that targets the spatiotemporal nature of wireless channels. Designed as a task-agnostic foundation model, LWM-Temporal learns universal channel embeddings that capture…

Human activity recognition (HAR) using drone-mounted cameras has attracted considerable interest from the computer vision research community in recent years. A robust and efficient HAR system has a pivotal role in fields like video…

Pruning is a neural network optimization technique that sacrifices accuracy in exchange for lower computational requirements. Pruning has been useful when working with extremely constrained environments in tinyML. Unfortunately, special…

Pooling is a simple but essential layer in modern deep CNN architectures for feature aggregation and extraction. Typical CNN design focuses on the conv layers and activation functions, while leaving the pooling layers with fewer options. We…

Semi-supervised video object segmentation (semi-VOS) is widely used in many applications. This task is tracking class-agnostic objects from a given target mask. For doing this, various approaches have been developed based on…