Related papers: Multi-Dialect Vietnamese: Task, Dataset, Baseline …

Visual Question Answering (VQA) is a fundamental multimodal task that requires models to jointly understand visual and textual information. Early VQA systems relied heavily on language biases, motivating subsequent work to emphasize visual…

Audio-driven talking head synthesis has achieved remarkable photorealism, yet state-of-the-art (SOTA) models exhibit a critical failure: they lack generalization to the full spectrum of human diversity in ethnicity, language, and age…

Goal: Numerous studies had successfully differentiated normal and abnormal voice samples. Nevertheless, further classification had rarely been attempted. This study proposes a novel approach, using continuous Mandarin speech instead of a…

Tibetan is a low-resource language with limited parallel speech corpora spanning its three major dialects (\"U-Tsang, Amdo, and Kham), limiting progress in speech modeling. To address this issue, we propose TMD-TTS, a unified Tibetan…

Recently, researchers set an ambitious goal of conducting speaker recognition in unconstrained conditions where the variations on ambient, channel and emotion could be arbitrary. However, most publicly available datasets are collected under…

In this technical report, we present VinaLLaMA, an open-weight, state-of-the-art (SOTA) Large Language Model for the Vietnamese language, built upon LLaMA-2 with an additional 800 billion trained tokens. VinaLLaMA not only demonstrates…

Robots are becoming everyday devices, increasing their interaction with humans. To make human-machine interaction more natural, cognitive features like Visual Voice Activity Detection (VVAD), which can detect whether a person is speaking or…

As speech generation technology advances, the risk of misuse through deepfake audio has become a pressing concern, which underscores the critical need for robust detection systems. However, many existing speech deepfake datasets are limited…

Mainstream Automatic Speech Recognition (ASR) systems excel at transcribing lexical content, but largely fail to recognize nonverbal vocalizations (NVs) embedded in speech, such as sighs, laughs, and coughs. This capability is important for…

Word segmentation and part-of-speech tagging are two critical preliminary steps for downstream tasks in Vietnamese natural language processing. In reality, people tend to consider also the phrase boundary when performing word segmentation…

Speech processing for low-resource dialects remains a fundamental challenge in developing inclusive and robust speech technologies. Despite its linguistic significance and large speaker population, the Wu dialect of Chinese has long been…

This paper introduces the development of the first open conversational speech dataset for the Isan language, the most widely spoken regional dialect in Thailand. Unlike existing speech corpora that are primarily based on read or scripted…

Understanding signboard text in natural scenes is essential for real-world applications of Visual Question Answering (VQA), yet remains underexplored, particularly in low-resource languages. We introduce ViSignVQA, the first large-scale…

In tackling the challenge of Multi-Document Summarization (MDS), numerous methods have been proposed, spanning both extractive and abstractive summarization techniques. However, each approach has its own limitations, making it less…

Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…

Aspect category detection (ACD) is one of the challenging tasks in the Aspect-based sentiment Analysis problem. The purpose of this task is to identify the aspect categories mentioned in user-generated reviews from a set of pre-defined…

The rapid advancement of large language models (LLMs) necessitates the development of new benchmarks to accurately assess their capabilities. To address this need for Vietnamese, this work aims to introduce ViLLM-Eval, the comprehensive…

Multi-Modal Large Language Models (MLLMs) have demonstrated impressive performance in various VQA tasks. However, they often lack interpretability and struggle with complex visual inputs, especially when the resolution of the input image is…

Current state of the art acoustic models can easily comprise more than 100 million parameters. This growing complexity demands larger training datasets to maintain a decent generalization of the final decision function. An ideal dataset is…

Visual Question Answering (VQA) has recently emerged as a potential research domain, captivating the interest of many in the field of artificial intelligence and computer vision. Despite the prevalence of approaches in English, there is a…