Related papers: Transcribing Bengali Text with Regional Dialects t…
Tibetan text-to-speech (TTS) has long been challenged by scarce speech resources, significant dialectal variation, and the complex mapping between written text and spoken pronunciation. To address these issues, this work presents, to the…
The applications of recurrent neural networks in machine translation are increasing in natural language processing. Besides other languages, Bangla language contains a large amount of vocabulary. Improvement of English to Bangla machine…
Machine dialect interpretation assumes a real part in encouraging man-machine correspondence and in addition men-men correspondence in Natural Language Processing (NLP). Machine Translation (MT) alludes to utilizing machine to change one…
Source-free domain generalization (SFDG) tackles the challenge of adapting models to unseen target domains without access to source domain data. To deal with this challenging task, recent advances in SFDG have primarily focused on…
Pretrained Large Language Models (LLM) such as ChatGPT, Claude, etc. have demonstrated strong capabilities in various fields of natural language generation. However, there are still many problems when using LLM in specialized…
Deepfake audio detection is challenging for low-resource languages like Bengali due to limited datasets and subtle acoustic features. To address this, we introduce BangalFake, a Bengali Deepfake Audio Dataset with 12,260 real and 13,260…
This paper introduces ClimateGPT, a model family of domain-specific large language models that synthesize interdisciplinary research on climate change. We trained two 7B models from scratch on a science-oriented dataset of 300B tokens. For…
Voice based applications are ruling over the era of automation because speech has a lot of factors that determine a speakers information as well as speech. Modern Automatic Speech Recognition (ASR) is a blessing in the field of…
Cross-domain and cross-compositional generalization of Text-to-SQL semantic parsing is a challenging task. Existing Large Language Model (LLM) based solutions rely on inference-time retrieval of few-shot exemplars from the training set to…
Standard-to-dialect machine translation remains challenging due to a persistent dialect gap in large language models and evaluation distortions inherent in n-gram metrics, which favor source copying over authentic dialect translation. In…
We introduce a new dataset for offline Handwritten Text Recognition (HTR) from images of Bangla scripts comprising words, lines, and document-level annotations. The BN-HTRd dataset is based on the BBC Bangla News corpus, meant to act as…
Text-to-Speech (TTS) system is a system where speech is synthesized from a given text following any particular approach. Concatenative synthesis, Hidden Markov Model (HMM) based synthesis, Deep Learning (DL) based synthesis with multiple…
Deep learning based text-to-speech (TTS) systems have been evolving rapidly with advances in model architectures, training methodologies, and generalization across speakers and languages. However, these advances have not been thoroughly…
Transient Electromagnetic (TEM) method is widely used in various geophysical applications, providing valuable insights into subsurface properties. However, time-domain TEM signals are often submerged in various types of noise. While recent…
As an Indo-Aryan language with limited available data, Chakma remains largely underrepresented in language models. In this work, we introduce a novel corpus of contextually coherent Bangla-transliterated Chakma, curated from Chakma…
Optical character recognition remains critical infrastructure for document digitization, yet state-of-the-art performance is often restricted to well-resourced institutions by prohibitive computational barriers. End-to-end transformer…
Despite astonishing progress, generating realistic images of complex scenes remains a challenging problem. Recently, layout-to-image synthesis approaches have attracted much interest by conditioning the generator on a list of bounding boxes…
This study proposes a language-agnostic transformer-based POS tagging framework designed for low-resource languages, using Bangla and Hindi as case studies. With only three lines of framework-specific code, the model was adapted from Bangla…
Purpose: Bangladesh's legal system struggles with major challenges like delays, complexity, high costs, and millions of unresolved cases, which deter many from pursuing legal action due to lack of knowledge or financial constraints. This…
In this paper, we propose a novel design for AI-native goal-oriented communications, exploiting transformer neural networks under dynamic inference constraints on bandwidth and computation. Transformers have become the standard architecture…