Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Chowdhury, Shammur Absar"'
Autor:
Mousi, Basel, Durrani, Nadir, Ahmad, Fatema, Hasan, Md. Arid, Hasanain, Maram, Kabbani, Tameem, Dalvi, Fahim, Chowdhury, Shammur Absar, Alam, Firoj
Arabic, with its rich diversity of dialects, remains significantly underrepresented in Large Language Models, particularly in dialectal variations. We address this gap by introducing seven synthetic datasets in dialects alongside Modern Standard Arab
Externí odkaz:
http://arxiv.org/abs/2409.11404
This paper presents a novel Dialectal Sound and Vowelization Recovery framework, designed to recognize borrowed and dialectal sounds within phonologically diverse and dialect-rich languages, that extends beyond its standard orthographic sound sets. T
Externí odkaz:
http://arxiv.org/abs/2408.02430
Autor:
Hasan, Md. Arid, Hasanain, Maram, Ahmad, Fatema, Laskar, Sahinur Rahman, Upadhyay, Sunaya, Sukhadia, Vrunda N, Kutlu, Mucahid, Chowdhury, Shammur Absar, Alam, Firoj
Natural Question Answering (QA) datasets play a crucial role in evaluating the capabilities of large language models (LLMs), ensuring their effectiveness in real-world applications. Despite the numerous QA datasets that have been developed, there is
Externí odkaz:
http://arxiv.org/abs/2407.09823
Self-supervised models have revolutionized speech processing, achieving new levels of performance in a wide variety of tasks with limited resources. However, the inner workings of these models are still opaque. In this paper, we aim to analyze the en
Externí odkaz:
http://arxiv.org/abs/2406.16099
Children's speech recognition is considered a low-resource task mainly due to the lack of publicly available data. There are several reasons for such data scarcity, including expensive data collection and annotation processes, and data privacy, among
Externí odkaz:
http://arxiv.org/abs/2406.13431
Autor:
Nandi, Rabindra Nath, Menon, Mehadi Hasan, Muntasir, Tareq Al, Sarker, Sagor, Muhtaseem, Quazi Sarwar, Islam, Md. Tariqul, Chowdhury, Shammur Absar, Alam, Firoj
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 a large-sc
Externí odkaz:
http://arxiv.org/abs/2311.03196
Pronunciation assessment and its application in computer-aided pronunciation training (CAPT) have seen impressive progress in recent years. With the rapid growth in language processing and deep learning over the past few years, there is a need for an
Externí odkaz:
http://arxiv.org/abs/2310.13974
Research on pronunciation assessment systems focuses on utilizing phonetic and phonological aspects of non-native (L2) speech, often neglecting the rich layer of information hidden within the non-verbal cues. In this study, we proposed a novel pronun
Externí odkaz:
http://arxiv.org/abs/2309.07739
The phonological discrepancies between a speaker's native (L1) and the non-native language (L2) serves as a major factor for mispronunciation. This paper introduces a novel multilingual MDD architecture, L1-MultiMDD, enriched with L1-aware speech rep
Externí odkaz:
http://arxiv.org/abs/2309.07719
Autor:
Dalvi, Fahim, Hasanain, Maram, Boughorbel, Sabri, Mousi, Basel, Abdaljalil, Samir, Nazar, Nizi, Abdelali, Ahmed, Chowdhury, Shammur Absar, Mubarak, Hamdy, Ali, Ahmed, Hawasly, Majd, Durrani, Nadir, Alam, Firoj
The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available, their cust
Externí odkaz:
http://arxiv.org/abs/2308.04945