相关论文: ARTT: Augmented Reverberant-Target Training for Un…

Advancements in monaural speech enhancement (SE) techniques have greatly improved the perceptual quality of speech. However, integrating these techniques into automatic speech recognition (ASR) systems has not yielded the expected…

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support…

Non-autoregressive (NAR) generation, which is first proposed in neural machine translation (NMT) to speed up inference, has attracted much attention in both machine learning and natural language processing communities. While NAR generation…

In the process of recording, storage and transmission of time-domain audio signals, errors may be introduced that are difficult to correct in an unsupervised way. Here, we train a convolutional deep neural network to re-synthesize input…

Deep neural networks (DNN) techniques have become pervasive in domains such as natural language processing and computer vision. They have achieved great success in these domains in task such as machine translation and image generation. Due…

Non-autoregressive (NAR) neural machine translation is usually done via knowledge distillation from an autoregressive (AR) model. Under this framework, we leverage large monolingual corpora to improve the NAR model's performance, with the…

The data scarcity in low-resource languages has become a bottleneck to building robust neural machine translation systems. Fine-tuning a multilingual pre-trained model (e.g., mBART (Liu et al., 2020)) on the translation task is a good…

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…

Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustness. In this work, we reveal a surprising…

Background noise and room reverberation are regarded as two major factors to degrade the subjective speech quality. In this paper, we propose an integrated framework to address simultaneous denoising and dereverberation under complicated…

Retrieval-augmented language models (LMs) have received much attention recently. However, typically the retriever is not trained jointly as a native component of the LM, but added post-hoc to an already-pretrained LM, which limits the…

When recorded in an enclosed room, a sound signal will most certainly get affected by reverberation. This not only undermines audio quality, but also poses a problem for many human-machine interaction technologies that use speech as their…

Non-autoregressive (NAR) language models are known for their low latency in neural machine translation (NMT). However, a performance gap exists between NAR and autoregressive models due to the large decoding space and difficulty in…

Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models…

Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…

The estimation of reverberation time from real-world signals plays a central role in a wide range of applications. In many scenarios, acoustic conditions change over time which in turn requires the estimate to be updated continuously.…

This paper proposes reverberation as supervision (RAS), a novel unsupervised loss function for single-channel reverberant speech separation. Prior methods for unsupervised separation required the synthesis of mixtures of mixtures or assumed…

Purpose: To develop a deep-learning-based image reconstruction framework for reproducible research in MRI. Methods: The BART toolbox offers a rich set of implementations of calibration and reconstruction algorithms for parallel imaging and…

Existing methods for image alignment struggle in cases involving feature-sparse regions, extreme scale and field-of-view differences, and large deformations, often resulting in suboptimal accuracy. Robustness to these challenges can be…

In this paper, we propose a multi-channel network for simultaneous speech dereverberation, enhancement and separation (DESNet). To enable gradient propagation and joint optimization, we adopt the attentional selection mechanism of the…