Related papers: Multi-query multi-head attention pooling and Inter…

Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-machine interaction in text-centric visual environments but also serves as a de facto gold proxy to evaluate AI models in the domain of…

The escalating context length in Large Language Models (LLMs) creates a severe performance bottleneck around the Key-Value (KV) cache, whose memory-bound nature leads to significant GPU under-utilization. This paper introduces Mixture of…

In recent years, financial sentiment analysis of public opinion has become increasingly important for market forecasting and risk assessment. However, existing methods often struggle to effectively integrate diverse opinion modalities and…

Multi-hop Question Answering (MHQA) adds layers of complexity to question answering, making it more challenging. When Language Models (LMs) are prompted with multiple search results, they are tasked not only with retrieving relevant…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…

Multi-channel target speaker extraction (MC-TSE) aims to extract a target speaker's voice from multi-speaker signals captured by multiple microphones. Existing methods often rely on auxiliary clues such as direction-of-arrival (DOA) or…

This paper presents an in-depth study of multimodal machine translation (MMT), examining the prevailing understanding that MMT systems exhibit decreased sensitivity to visual information when text inputs are complete. Instead, we attribute…

While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades…

The short duration of an input utterance is one of the most critical threats that degrade the performance of speaker verification systems. This study aimed to develop an integrated text-independent speaker verification system that inputs…

Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models. However, existing models for MQA under KE exhibit poor performance when dealing with questions…

Speaker diarization systems are challenged by a trade-off between the temporal resolution and the fidelity of the speaker representation. By obtaining a superior temporal resolution with an enhanced accuracy, a multi-scale approach is a way…

This paper presents an improved deep embedding learning method based on convolutional neural network (CNN) for text-independent speaker verification. Two improvements are proposed for x-vector embedding learning: (1) Multi-scale convolution…

We introduce a new automatic evaluation method for speaker similarity assessment, that is consistent with human perceptual scores. Modern neural text-to-speech models require a vast amount of clean training data, which is why many solutions…

Following the successful hosts of the 1-st (NLPCC 2023 Foshan) CMIVQA and the 2-rd (NLPCC 2024 Hangzhou) MMIVQA challenges, this year, a new task has been introduced to further advance research in multi-modal, multilingual, and multi-hop…

In this paper, we consider the problem of minimizing a smooth objective over multiple rank constraints on Hankel-structured matrices. This kind of problems arises in system identification, system theory and signal processing, where the rank…

Speaker verification based on ad-hoc microphone arrays has the potential of reducing the error significantly in adverse acoustic environments. However, existing approaches extract utterance-level speaker embeddings from each channel of an…

KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from…

Fusing multi-modality information is known to be able to effectively bring significant improvement in video classification. However, the most popular method up to now is still simply fusing each stream's prediction scores at the last stage.…

This paper discribes the DKU-DukeECE submission to the 4th track of the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22). Our system contains a fused voice activity detection model, a clustering-based diarization model, and a…

Audio-visual quality assessment (AVQA) is essential for streaming, teleconferencing, and immersive media. In realistic streaming scenarios, distortions are often asymmetric, where one modality may be severely degraded while the other…