Related papers: Transcribing Bengali Text with Regional Dialects t…

Handwritten character classification in the Bengali script is a significant challenge due to the complexity and variability of the characters. The models commonly used for classification are often computationally expensive and data-hungry,…

Discrete audio tokens derived from self-supervised learning models have gained widespread usage in speech generation. However, current practice of directly utilizing audio tokens poses challenges for sequence modeling due to the length of…

Finding local invariant patterns in handwrit-ten characters and/or digits for optical character recognition is a difficult task. Variations in writing styles from one person to another make this task challenging. We have proposed a…

IR in low-resource languages remains limited by the scarcity of high-quality, task-specific annotated datasets. Manual annotation is expensive and difficult to scale, while using large language models (LLMs) as automated annotators…

Technology is the making, usage and knowledge of tools, techniques, crafts, systems or methods of organization in order to solve a problem or serve some purpose. This is true for humanitarian issues also. Such as the issue of language and…

Regional language extraction from a natural scene image is always a challenging proposition due to its dependence on the text information extracted from Image. Text Extraction on the other hand varies on different lighting condition,…

We present a speaker conditioned text-to-speech (TTS) system aimed at addressing challenges in generating speech for unseen speakers and supporting diverse Indian languages. Our method leverages a diffusion-based TTS architecture, where a…

We present the Multilingual Cloud Corpus, the first national-scale, parallel, multimodal linguistic dataset of Bangladesh's ethnic and indigenous languages. Despite being home to approximately 40 minority languages spanning four language…

One of the major challenges for developing automatic speech recognition (ASR) for low-resource languages is the limited access to labeled data with domain-specific variations. In this study, we propose a pseudo-labeling approach to develop…

Current Machine Translation (MT) systems for Arabic often struggle to account for dialectal diversity, frequently homogenizing dialectal inputs into Modern Standard Arabic (MSA) and offering limited user control over the target vernacular.…

Question-answering systems for Bengali have seen limited development, particularly in domain-specific applications. Leveraging advancements in natural language processing, this paper explores a fine-tuned BERT-Bangla model to address this…

Although Automatic Speech Recognition (ASR) in Bengali has seen significant progress, processing long-duration audio and performing robust speaker diarization remain critical research gaps. To address the severe scarcity of joint ASR and…

Speech recognition is a fascinating process that offers the opportunity to interact and command the machine in the field of human-computer interactions. Speech recognition is a language-dependent system constructed directly based on the…

Scene text recognition in low-resource Indian languages is challenging because of complexities like multiple scripts, fonts, text size, and orientations. In this work, we investigate the power of transfer learning for all the layers of deep…

Large language models work well for technical problem solving in English but perform poorly when the same questions are asked in Bangla. A simple solution would be to translate Bangla questions into English first and then use these models.…

Spoken term detection (STD) is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching, limiting its practicality. To address these challenges, we propose a novel approach that…

Handwriting recognition remains challenging for some of the most spoken languages, like Bangla, due to the complexity of line and word segmentation brought by the curvilinear nature of writing and lack of quality datasets. This paper solves…

Bangla or Bengali is the national language of Bangladesh, people from different regions don't talk in proper Bangla. Every division of Bangladesh has its own local language like Sylheti, Chittagong etc. In recent years some papers were…

Despite the high-quality results of text-to-image generation, stereotypical biases have been spotted in their generated contents, compromising the fairness of generative models. In this work, we propose to learn adaptive inclusive tokens to…

Recent advancements in prompt tuning have successfully adapted large-scale models like Contrastive Language-Image Pre-trained (CLIP) for downstream tasks such as scene text detection. Typically, text prompt complements the text encoder's…