相关论文: Lattice-based Improvements for Voice Triggering Us…

Graph Neural Networks (GNNs) have been widely applied to various fields due to their powerful representations of graph-structured data. Despite the success of GNNs, most existing GNNs are designed to learn node representations on the fixed…

Conversational AI systems require guardrails to prevent harmful outputs, yet existing approaches use static rules that cannot adapt to new threats or deployment contexts. We introduce Lattice, a framework for self-constructing and…

LLM-based automatic speech recognition models demonstrate strong performance by connecting audio encoders and LLMs. However, data scarcity of paired speech and transcription often hinders their adaptation to new domains, making text-only…

With the proliferation of social media, the detection of fake news has become a critical issue that poses a significant threat to society. The dissemination of fake information can lead to social harm and damage the credibility of…

Functional Magnetic Resonance Imaging (fMRI) provides useful insights into the brain function both during task or rest. Representing fMRI data using correlation matrices is found to be a reliable method of analyzing the inherent…

Current deep neural network (DNN) based speech separation faces a fundamental challenge -- while the models need to be trained on short segments due to computational constraints, real-world applications typically require processing…

Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) is the key technique for remote sensing image recognition. The state-of-the-art works exploit the deep convolutional neural networks (CNNs) for SAR ATR, leading to high…

Graph Neural Networks (GNNs) have gained considerable prominence in semi-supervised learning tasks in processing graph-structured data, primarily owing to their message-passing mechanism, which largely relies on the availability of clean…

Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder…

Despite recent advances in training and prompting strategies for Large Language Models (LLMs), these models continue to face challenges with complex logical reasoning tasks that involve long reasoning chains. In this work, we explore the…

Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned their faithfulness, as they may not accurately reflect the…

Sequence discriminative training criteria have long been a standard tool in automatic speech recognition for improving the performance of acoustic models over their maximum likelihood / cross entropy trained counterparts. While previously a…

Target speech extraction (TSE) has achieved strong performance in relatively simple conditions such as one-speaker-plus-noise and two-speaker mixtures, but its performance remains unsatisfactory in noisy multi-speaker scenarios. To address…

We propose a neural network-based speech enhancement (SE) method called the phase-aware recurrent two stage network (rTSN). The rTSN is an extension of our previously proposed two stage network (TSN) framework. This TSN framework was…

We describe an implementation of gradient boosting and neural guidance of saturation-style automated theorem provers that does not depend on consistent symbol names across problems. For the gradient-boosting guidance, we manually create…

Automatic Speech Recognition (ASR) can be used as the assistance of speech communication between pilots and air-traffic controllers. Its application can significantly reduce the complexity of the task and increase the reliability of…

Grammatical error correction, like other machine learning tasks, greatly benefits from large quantities of high quality training data, which is typically expensive to produce. While writing a program to automatically generate realistic…

Graph Self-Supervised Learning (GSSL) offers a powerful paradigm for learning graph representations without labeled data. However, existing work assumes clean, manually curated graphs. Recent advances in NLP enable the large-scale automatic…

The ability to reason with natural language is a fundamental prerequisite for many NLP tasks such as information extraction, machine translation and question answering. To quantify this ability, systems are commonly tested whether they can…

Automatic Speech Recognition (ASR), as the assistance of speech communication between pilots and air-traffic controllers, can significantly reduce the complexity of the task and increase the reliability of transmitted information. ASR…