Related papers: InsNet: An Efficient, Flexible, and Performant Ins…

Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant single-modality (text and video) data without…

Standard decoders for neural machine translation autoregressively generate a single target token per time step, which slows inference especially for long outputs. While architectural advances such as the Transformer fully parallelize the…

Deep learning based methods hold state-of-the-art results in image denoising, but remain difficult to interpret due to their construction from poorly understood building blocks such as batch-normalization, residual learning, and feature…

Inference for Deep Neural Networks is increasingly being executed locally on mobile and embedded platforms due to its advantages in latency, privacy and connectivity. Since modern System on Chips typically execute a combination of different…

Denoising Diffusion Probabilistic Models have shown extraordinary ability on various generative tasks. However, their slow inference speed renders them impractical in speech synthesis. This paper proposes a linear diffusion model (LinDiff)…

Real-time semantic segmentation is a challenging task that requires high-accuracy models with low-inference times. Implementing these models on embedded systems is limited by hardware capability and memory usage, which produces bottlenecks.…

Text generating capabilities have undergone a substantial transformation with the introduction of large language models (LLMs). Electroencephalography (EEG)-based text production is still difficult, though, because it requires a lot of data…

Non-autoregressive neural machine translation (NAT) models are proposed to accelerate the inference process while maintaining relatively high performance. However, existing NAT models are difficult to achieve the desired efficiency-quality…

Modern approaches to text to speech require the entire input character sequence to be processed before any audio is synthesised. This latency limits the suitability of such models for time-sensitive tasks like simultaneous interpretation.…

Scene text synthesis involves rendering specified texts onto arbitrary images. Current methods typically formulate this task in an end-to-end manner but lack effective character-level guidance during training. Besides, their text encoders,…

Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples. We develop a new generative model called…

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be…

We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our…

In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech…

We present a novel, real-time, semantic segmentation network in which the encoder both encodes and generates the parameters (weights) of the decoder. Furthermore, to allow maximal adaptivity, the weights at each decoder block vary…

In this article we show how the problem of neural text generation can be constructively reformulated in terms of transitions between the states of a finite-state machine. This framework leads to an efficient approach to guiding text…

Matching images and sentences demands a fine understanding of both modalities. In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply…

We introduce a new way of learning to encode position information for non-recurrent models, such as Transformer models. Unlike RNN and LSTM, which contain inductive bias by loading the input tokens sequentially, non-recurrent models are…

How to aggregate information from multiple instances is a key question multiple instance learning. Prior neural models implement different variants of the well-known encoder-decoder strategy according to which all input features are encoded…