Related papers: A Curriculum Learning Method for Improved Noise Ro…

Recent advancements in Automatic Piano Transcription (APT) have significantly improved system performance, but the impact of noisy environments on the system performance remains largely unexplored. This study investigates the impact of…

Neural network language model (NNLM) plays an essential role in automatic speech recognition (ASR) systems, especially in adaptation tasks when text-only data is available. In practice, an NNLM is typically trained on a combination of data…

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been…

As wireless communication systems evolve, automatic modulation recognition (AMR) plays a key role in improving spectrum efficiency, especially in cognitive radio systems. Traditional AMR methods face challenges in complex, noisy…

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent…

Speech enhancement (SE) aims to reduce noise in speech signals. Most SE techniques focus only on addressing audio information. In this work, inspired by multimodal learning, which utilizes data from different modalities, and the recent…

Existing audio analysis methods generally first transform the audio stream to spectrogram, and then feed it into CNN for further analysis. A standard CNN recognizes specific visual patterns over feature map, then pools for high-level…

Dialogue policy learning based on reinforcement learning is difficult to be applied to real users to train dialogue agents from scratch because of the high cost. User simulators, which choose random user goals for the dialogue agent to…

This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial…

End-to-end Automatic Speech Recognition (ASR) systems based on neural networks have seen large improvements in recent years. The availability of large scale hand-labeled datasets and sufficient computing resources made it possible to train…

Recently, self-supervised pre-training has gained success in automatic speech recognition (ASR). However, considering the difference between speech accents in real scenarios, how to identify accents and use accent features to improve ASR is…

While integrating speech encoder with LLM requires substantial data and resources, use cases face limitations due to insufficient availability. To address this, we propose a solution with a parameter-efficient adapter that converts speech…

Recently, extensive studies in Reinforcement Learning have been carried out on the ability of transformers to adapt in-context to various environments and tasks. Current in-context RL methods are limited by their strict requirements for…

Existing research suggests that automatic speech recognition (ASR) models can benefit from additional contexts (e.g., contact lists, user specified vocabulary). Rare words and named entities can be better recognized with contexts. In this…

The segmentation of coronary arteries in X-ray angiograms by convolutional neural networks (CNNs) is promising yet limited by the requirement of precisely annotating all pixels in a large number of training images, which is extremely…

Process reward models (PRMs) offer fine-grained, step-level evaluations that facilitate deeper reasoning processes in large language models (LLMs), proving effective in complex tasks like mathematical reasoning. However, developing PRMs is…

Depth estimation is a traditional computer vision task, which plays a crucial role in understanding 3D scene geometry. Recently, deep-convolutional-neural-networks based methods have achieved promising results in the monocular depth…

Active Learning (AL) aims to reduce annotation costs by strategically selecting the most informative samples for labeling. However, most active learning methods struggle in the low-budget regime where only a few labeled examples are…

In this work, we exploit speech enhancement for improving a recurrent neural network transducer (RNN-T) based ASR system. We employ a dense convolutional recurrent network (DCRN) for complex spectral mapping based speech enhancement, and…

Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker…