Related papers: TCDA: Thread-Constrained Discourse-Aware Modeling …

Multimodal Sentiment Analysis (MSA) integrates language, visual, and acoustic modalities to infer human sentiment. Most existing methods either focus on globally shared representations or modality-specific features, while overlooking…

Modern deep learning approaches have achieved groundbreaking performance in modeling and classifying sequential data. Specifically, attention networks constitute the state-of-the-art paradigm for capturing long temporal dynamics. This paper…

Distantly supervised relation extraction has been widely applied in knowledge base construction due to its less requirement of human efforts. However, the automatically established training datasets in distant supervision contain…

The problem of building a coherent and non-monotonous conversational agent with proper discourse and coverage is still an area of open research. Current architectures only take care of semantic and contextual information for a given query…

Sequence-to-Sequence (Seq2Seq) models have witnessed a notable success in generating natural conversational exchanges. Notwithstanding the syntactically well-formed responses generated by these neural network models, they are prone to be…

Dialogue-based relation extraction (DiaRE) aims to detect the structural information from unstructured utterances in dialogues. Existing relation extraction models may be unsatisfactory under such a conversational setting, due to the…

Hallucinations can be produced by conversational AI systems, particularly in multi-turn conversations where context changes and contradictions may eventually surface. By representing the entire conversation as a temporal graph, we present a…

We identify a core failure mode that occurs when using the usual linear interpolation on rotary positional embeddings (RoPE) for mixed-resolution denoising with Diffusion Transformers. When tokens from different spatial grids are mixed, the…

Conversational question answering (CQA) is a novel QA task that requires understanding of dialogue context. Different from traditional single-turn machine reading comprehension (MRC) tasks, CQA includes passage comprehension, coreference…

We propose Text-Aligned Speech Tokens with Multiple Layer-Aggregation (TASLA), which is a text-aligned speech tokenization framework that aims to address the problem that under a low-frame-rate and text-aligned regime, single-source speech…

Trajectory Representation Learning (TRL) is a powerful tool for spatial-temporal data analysis and management. TRL aims to convert complicated raw trajectories into low-dimensional representation vectors, which can be applied to various…

Graph representation learning has become a hot research topic due to its powerful nonlinear fitting capability in extracting representative node embeddings. However, for sequential data such as speech signals, most traditional methods…

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by complex physiological processes. Previous research has predominantly focused on static cerebral interactions, often neglecting the brain's dynamic nature and…

Conventional time-delay neural networks (TDNNs) struggle to handle long-range context, their ability to represent speaker information is therefore limited in long utterances. Existing solutions either depend on increasing model complexity…

This paper summarizes our submission to Task 2 of the second track of the 10th Dialog System Technology Challenge (DSTC10) "Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations". Similar to the previous year's…

While deep learning has advanced speech enhancement (SE), effective phase modeling remains challenging, as conventional networks typically operate within a flat Euclidean feature space, which is not easy to model the underlying circular…

Representation learning on dynamic graphs requires capturing complex dependencies that evolve across both time and structure. Existing approaches typically adopt fixed temporal decay schemes or predetermined structural propagation depths,…

Dynamic Text-Attributed Graphs (DyTAGs) are a novel graph paradigm that captures evolving temporal events (edges) alongside rich textual attributes. Existing studies can be broadly categorized into TGNN-driven and LLM-driven approaches,…

This paper introduces OmniGSE, a novel general speech enhancement (GSE) framework designed to mitigate the diverse distortions that speech signals encounter in real-world scenarios. These distortions include background noise, reverberation,…

Current speaker verification techniques rely on a neural network to extract speaker representations. The successful x-vector architecture is a Time Delay Neural Network (TDNN) that applies statistics pooling to project variable-length…