相关论文: Keyword Transformer: A Self-Attention Model for Ke…

Transformers have become an indispensable module for text generation models since their great success in machine translation. Previous works attribute the~success of transformers to the query-key-value dot-product attention, which provides…

Keyword spotting (KWS) plays an essential role in enabling speech-based user interaction on smart devices, and conventional KWS (C-KWS) approaches have concentrated on detecting user-agnostic pre-defined keywords. However, in practice, most…

Keyword spotting (KWS) is a key component of smart devices, enabling efficient and intuitive audio interaction. However, standard KWS systems deployed on embedded devices often suffer performance degradation under real-world operating…

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention…

Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attention computed by…

Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outstanding performance of self-attention models is their ability…

The task of Stance Detection involves discerning the stance expressed in a text towards a specific subject or target. Prior works have relied on existing transformer models that lack the capability to prioritize targets effectively.…

In this paper, we propose an extension to Longformer Encoder-Decoder, a popular sparse transformer architecture. One common challenge with sparse transformers is that they can struggle with encoding of long range context, such as…

Keyword spotting (KWS) on mobile devices generally requires a small memory footprint. However, most current models still maintain a large number of parameters in order to ensure good performance. In this paper, we propose a temporally…

Latest development of neural models has connected the encoder and decoder through a self-attention mechanism. In particular, Transformer, which is solely based on self-attention, has led to breakthroughs in Natural Language Processing (NLP)…

Many image understanding tasks involve identifying what is present and where it appears. However, tasks that address where, such as object discovery, detection, and segmentation, are often considerably more complex than image…

Transformer-based models have significantly advanced natural language processing and computer vision in recent years. However, due to the irregular and disordered structure of point cloud data, transformer-based models for 3D deep learning…

End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty recognizing uncommon words, that appear infrequently in the training data. One promising method, to improve the recognition accuracy on such rare words, is to…

The self-attention mechanism, a cornerstone of Transformer-based state-of-the-art deep learning architectures, is largely heuristic-driven and fundamentally challenging to interpret. Establishing a robust theoretical foundation to explain…

Spoken keyword spotting (KWS) aims to identify keywords in audio for wide applications, especially on edge devices. Current small-footprint KWS systems focus on efficient model designs. However, their inference performance can decline in…

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and…

The quadratic cost of attention in transformers motivated the development of efficient approaches: namely sparse and sliding window attention, convolutions and linear attention. Although these approaches result in impressive reductions in…

Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising…

The paradigm of Transformers using the self-attention mechanism has manifested its advantage in learning graph-structured data. Yet, Graph Transformers are capable of modeling full range dependencies but are often deficient in extracting…

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…