Monitoring AI enhancements in Urdu
Latest Urdu-focused AI updates and research-backed news
Researchat Paediatrics & Child Health Maternal & Child health Omics Polio Full list of active grants Our independent investigators Academic Programmes Recent Artificial Intelligence These are the active grants at the Department of Paediatrics which focus on large language models and machine learning providing solutions for healthcare.
Open Full NewsAccepted Main ConferencePapersEcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song TAGExplainer: Narrating Graph ...
Open Full NewsAbstract:State-of-the-artspeech…▽ MoreState-of-the-artspeechrecognitionsystems rely heavily on three basic components: an acoustic model, a pronunciation lexicon and a language model. To build these components, a researcher needs linguistic as well as technical expertise, which is a barrier in low-resource domains. Techniques to construct these three components without having expert domain knowled
Open Full NewsAbstract:…of visual expressions learning to decode spoken words. Now-a-days, with the help of deep learning it is possible to translate lip sequences into meaningful words. Thespeech…▽ MoreHuman lip-reading is a challenging task. It requires not only knowledge of underlying language but also visual clues to predict spoken words. Experts need certain level of experience and understanding of visual
Open Full NewsAbstract:Cross-lingualspeechemotion…▽ MoreCross-lingualspeechemotionrecognitionis an important task for practical applications. The performance of automaticspeechemotionrecognitionsystems degrades in cross-corpus scenarios, particularly in scenarios involving multiple languages or a previously unseen language such asUrdufor which limited or no data is available. In this study, we investigate the p
Open Full NewsAbstract:Cross-lingualspeechemotion…▽ MoreCross-lingualspeechemotionrecognition(SER) is a crucial task for many real-world applications. The performance of SER systems is often degraded by the differences in the distributions of training and test data. These differences become more apparent when training and test data belong to different languages, which cause a significant performance gap between
Open Full NewsAbstract:It has been established thatSpeechAffect…▽ MoreIt has been established thatSpeechAffectRecognitionfor low resource languages is a difficult task. Here we present a Transfer learning basedSpeechAffectRecognitionapproach in which: we pre-train a model for high resource language affectrecognitiontask and fine tune the parameters for low resource language using Deep Residual Network. Here we
Open Full NewsAbstract:SpeechAffect…▽ MoreSpeechAffectRecognitionis a problem of extracting emotional affects from audio data. Low resource languages corpora are rear and affectrecognitionis a difficult task in cross-corpus settings. We present an approach in which the model is trained on high resource language and fine-tune to recognize affects in low resource language. We train the model in same corpus settin
Open Full NewsAbstract:Designing reliableSpeechEmotion…▽ MoreDesigning reliableSpeechEmotionRecognitionsystems is a complex task that inevitably requires sufficient data for training purposes. Such extensive datasets are currently available in only a few languages, including English, German, and Italian. In this paper, we present SEMOUR, the first scripted database of emotion-taggedspeechin theUrdulanguage, to
Open Full NewsAbstract:SpeechEmotion…▽ MoreSpeechEmotionRecognition(SER) in a single language has achieved remarkable results through deep learning approaches in the last decade. However, cross-lingual SER remains a challenge in real-world applications due to a great difference between the source and target domain distributions. To address this issue, we propose an unsupervised cross-lingual Neural Network with
Open Full NewsAbstract:…for TTS in low-resource languages. We use diverse source languages (English, Finnish, Hindi, Japanese, and Russian) and target languages (Bulgarian, Georgian, Kazakh, Swahili,Urdu, and Uzbek) to test the language-independence of the methods and enhance the findings' applicability. We use Character Error Rates from automatic…▽ MoreWe compare using a PHOIBLE-based phone mapping method and
Open Full NewsAbstract:In a conventionalSpeechemotion…▽ MoreIn a conventionalSpeechemotionrecognition(SER) task, a classifier for a given language is trained on a pre-existing dataset for that same language. However, where training data for a language does not exist, data from other languages can be used instead. We experiment with cross-lingual and multilingual SER, working with Amharic, English, German andURD
Open Full News