Asif Azad

Asif Azad, MD Sadik Hossain Shanto, Mohammad Sadat Hossain et al.

Automated phoneme-level pronunciation assessment is vital for scalable speech therapy and language learning, yet validated tools for Arabic remain scarce. We present Harf-Speech, a modular system scoring Arabic pronunciation at the phoneme level on a clinical scale. It combines an MSA phonetizer, a fine-tuned speech-to-phoneme model, Levenshtein alignment, and a blended scorer using longest common subsequence and edit-distance metrics. We fine-tune three ASR architectures on Arabic phoneme data and benchmark them with zero-shot multimodal models; the best, OmniASR-CTC-1B-v2, achieves 8.92\% phoneme error rate. Three certified speech-language pathologists independently scored 40 utterances for clinical validation. Harf-Speech attains a Pearson correlation of 0.791 and ICC(2,1) of 0.659 with mean expert scores, outperforming existing end-to-end assessment frameworks. These results show Harf-Speech yields clinically aligned, interpretable scores comparable to inter-rater expert agreement.

Ashrafur Rahman Khan, Asif Azad

In the rapidly evolving digital era, the analysis of document layouts plays a pivotal role in automated information extraction and interpretation. In our work, we have trained MViTv2 transformer model architecture with cascaded mask R-CNN on BaDLAD dataset to extract text box, paragraphs, images and tables from a document. After training on 20365 document images for 36 epochs in a 3 phase cycle, we achieved a training loss of 0.2125 and a mask loss of 0.19. Our work extends beyond training, delving into the exploration of potential enhancement avenues. We investigate the impact of rotation and flip augmentation, the effectiveness of slicing input images pre-inference, the implications of varying the resolution of the transformer backbone, and the potential of employing a dual-pass inference to uncover missed text-boxes. Through these explorations, we observe a spectrum of outcomes, where some modifications result in tangible performance improvements, while others offer unique insights for future endeavors.

Asif Azad, Mohammad Sadat Hossain, MD Sadik Hossain Shanto et al.

Children with Autism Spectrum Disorder in Arabic-speaking countries face compounded barriers to effective speech and language therapy: a shortage of qualified specialists, limited service reach beyond urban centers, and a near-total absence of culturally grounded digital therapy materials. We present Digital Harf, a pervasive, multimodal AI platform that extends clinician-led speech and language therapy into the home. The system integrates three therapeutic modules - language therapy, speech intelligibility, and picture description - within a unified workflow that adapts to each child's performance over time. To address the critical shortage of Arabic therapy content, we introduce an Agentic Synthetic Data Engine (ASDE) that automatically generates culturally relevant images, prompts, and language tasks guided by explicit therapeutic and cultural criteria. Expert evaluation with 13 licensed Speech-Language Pathologists yielded a 90.1% clinical acceptance rate for ASDE-generated content without any manual curation or selection, and strong ratings for cultural and linguistic alignment across the full platform. Digital Harf demonstrates that AI-driven therapeutic systems can be built from the ground up for underrepresented linguistic settings, treating cultural grounding as core infrastructure rather than an adaptation afterthought.

Asif Azad, Mohammad Sadat Hossain, MD Sadik Hossain Shanto et al.

Vision-Language Models (VLMs) have achieved remarkable progress in complex visual understanding across scientific and reasoning tasks. While performance benchmarking has advanced our understanding of these capabilities, the critical dimension of uncertainty quantification has received insufficient attention. Therefore, unlike prior conformal prediction studies that focused on limited settings, we conduct a comprehensive uncertainty benchmarking study, evaluating 16 state-of-the-art VLMs (open and closed-source) across 6 multimodal datasets with 3 distinct scoring functions. Our findings demonstrate that larger models consistently exhibit better uncertainty quantification; models that know more also know better what they don't know. More certain models achieve higher accuracy, while mathematical and reasoning tasks elicit poorer uncertainty performance across all models compared to other domains. This work establishes a foundation for reliable uncertainty evaluation in multimodal systems.