检索结果-内蒙古大学图书馆

1st Workshop on Challenges in Processing South Asian languages, CHiPSal 2025, co-located with the 31st International Conference on Computational Linguistics, COLING 2025

作者： Tahir, Munief Hassan Shams, Sana Fiaz, Layba Adeeba, Farah Hussain, Sarmad Center for Language Engineering Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Lahore Pakistan

ISBN: (纸本)9798891762015

Large language Models (LLMs) pre-trained on multilingual data have revolutionized natural language processing research, by transitioning from languages and task specific model pipelines to a single model adapted on a variety of tasks. However majority of existing multilingual NLP benchmarks for LLMs provide evaluation data in only few languages with little linguistic diversity. In addition these benchmarks lack quality assessment against the respective state-of the art models. This study presents an in-depth examination of 7 prominent LLMs: GPT-3.5-turbo, Llama 2-7B-Chat, Llama 3.1-8B, Bloomz 3B, Bloomz 7B1, Ministral-8B and Whisper (Large, medium and small variant) across 17 tasks using 22 datasets, 13.8 hours of speech, in a zero-shot setting, and their performance against state-of-the-art (SOTA) models, has been compared and analyzed. Our experiments show that SOTA models currently outperform encoder-decoder models in majority of Urdu NLP tasks under zero-shot settings. However, comparing Llama 3.1-8B over prior version Llama 2-7B-Chat, we can deduce that with improved language coverage, LLMs can surpass these SOTA models. Our results emphasize that models with fewer parameters but richer language-specific data, like Llama 3.1-8B, often outperform larger models with lower language diversity, such as GPT-3.5, in several tasks. © 2025 International Committee on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Acoustic Realization of /S/ Across Accents of Urdu 27

Acoustic Realization of /S/ Across Accents of Urdu

引用

27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024

作者： Fatima, Iram Rauf, Sahar Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Center for Language Engineering Lahore Pakistan

ISBN: (纸本)9798331506032

This study investigates acoustic characteristics that distinguish three Urdu accents spoken predominantly in Punjab: Pothowari, Multani, and Jhangochi. We examined four spectral moments - center of gravity (CoG), standard deviation (SD), skewness, and kurtosis - of the fricative /s/ to identify acoustic variations between these accents. 1200 /s/ tokens were annotated from a spontaneous speech corpus, focusing on 10 speakers per accent (5 male, 5 female), with 40 tokens per speaker. The results reveal distinct ordering of accents by CoG values, along with notable patterns in SD, skewness, and kurtosis, offering deeper insight into accent-based differences. Additionally, our findings demonstrate gender-specific changes in the energy trajectories of the fricative within each accent. These findings contribute to a better understanding of Urdu's phonetic diversity and have broader implications for speech processing, sociolinguistics, and practical applications such as accent recognition in speech technologies. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Bridging the Bandwidth Gap: A Mixed Band Telephonic Urdu ASR Approach with Domain Adaptation for Banking Applications 1

Bridging the Bandwidth Gap: A Mixed Band Telephonic Urdu ASR...

引用

1st Workshop on Challenges in Processing South Asian languages, CHiPSal 2025, co-located with the 31st International Conference on Computational Linguistics, COLING 2025

作者： Khalid, Ayesha Adeeba, Farah Sehar, Najm Ul Hussain, Sarmad Center for Language Engineering Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Lahore Pakistan Department of Computer Science University of Engineering and Technology New Campus Pakistan

ISBN: (纸本)9798891762015

The accuracy of Automatic Speech Recognition (ASR) systems is influenced by the quality and context of speech signals, particularly in telephonic environments prone to errors like channel drops and noise, leading to higher Word Error Rates (WER). This paper presents the development of a large vocabulary Urdu ASR system for telephonic speech, based on a corpus of 445 speakers from diverse domains. The corpus, annotated at the sentence level, is used to train and evaluate GMM-HMM and chain Time-Delay Neural Network (TDNN) models on a 10-hour test set. Results show that the TDNN model outperforms GMM-HMM. Mixing narrowband and wideband speech further reduces WER. The test sets are also evaluated for the pre-trained model Whisper for performance comparison. Additionally, system adaptation for the banking domain with a specialized lexicon and language model demonstrates the system’s potential for domain-specific applications. © 2025 International Committee on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings

arXiv

引用

arXiv 2025年

作者： Fiaz, Layba Tahir, Munief Hassan Shams, Sana Hussain, Sarmad Center for Language Engineering Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Lahore Pakistan

Multilingual Large language Models (LLMs) often provide suboptimal performance on low-resource languages like Urdu. This paper introduces UrduLLaMA 1.0, a model derived from the open-source Llama-3.1-8B-Instruct architecture and continually pre-trained on 128 million Urdu tokens, capturing the rich diversity of the language. To enhance instruction-following and translation capabilities, we leverage Low-Rank Adaptation (LoRA) to fine tune the model on 41,000 Urdu instructions and approximately 50,000 English-Urdu translation pairs. Evaluation across three machine translation datasets demonstrates significant performance improvements compared to state-of-the-art (SOTA) models, establishing a new benchmark for Urdu LLMs. These findings underscore the potential of targeted adaptation strategies with limited data and computational resources to address the unique challenges of low-resource languages. © 2025, CC BY-NC-SA.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Acoustic Realization of /S/ Across Accents of Urdu

Acoustic Realization of /S/ Across Accents of Urdu

引用

Oriental COCOSDA International Conference on Speech Database and Assessments

作者： Iram Fatima Sahar Rauf Center for Language Engineering Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Lahore

ISBN: (数字)9798331506032

ISBN: (纸本)9798331506049

This study investigates acoustic characteristics that distinguish three Urdu accents spoken predominantly in Punjab: Pothowari, Multani, and Jhangochi. We examined four spectral moments—center of gravity (CoG), standard deviation (SD), skewness, and kurtosis—of the fricative /s/ to identify acoustic variations between these accents. 1200 /s/ tokens were annotated from a spontaneous speech corpus, focusing on 10 speakers per accent (5 male, 5 female), with 40 tokens per speaker. The results reveal distinct ordering of accents by CoG values, along with notable patterns in SD, skewness, and kurtosis, offering deeper insight into accent-based differences. Additionally, our findings demonstrate gender-specific changes in the energy trajectories of the fricative within each accent. These findings contribute to a better understanding of Urdu's phonetic diversity and have broader implications for speech processing, sociolinguistics, and practical applications such as accent recognition in speech technologies.

关键词： Statistical analysis Focusing Speech recognition Phonetics Acoustics Kurtosis Trajectory Speech processing Standards Gravity

来源：评论

学校读者我要写书评

暂无评论

Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks

arXiv

引用

arXiv 2024年

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

O-COCOSDA Country Report of Pakistan 23

O-COCOSDA Country Report of Pakistan

引用

23rd Conference of the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2020

作者： Habib, Tania Hussain, Sarmad Center for Language Engineering Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Lahore Pakistan

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-Based Weighted Federated Machine Learning Approach for Sustainable Energy Management with IoE Integration

Fuzzy-Based Weighted Federated Machine Learning Approach for...

引用

2024 Systems and Information engineering Design Symposium, SIEDS 2024

作者： Ghazal, Taher M. Iqbal Janjua, Jamshaid Abbas, Sagheer Fatima, Areej Saleem, Muhammad Khan, Muhammad Adnan alqarafi, Abdulrahman Khalifa University Centre for Cyber Physical Systems Computer Science Department Abu Dhabi United Arab Emirates Universiti Kebangsaan Malaysia Center for Cyber Security Faculty of Information Science and Technology Selangor Malaysia National College of Business Administration and Economics School of Computer Sciences Lahore Pakistan Al-Khawarizmi Institute of Computer Science Lahore Pakistan Bahria University Department of Computer Science Lahore Pakistan LGU Department of Computer Science Lahore Pakistan Minhaj University School of Computer Science Lahore Pakistan Skyline University College School of Computing Sharjah United Arab Emirates Riphah International University Riphah School of Computing and Innovation Lahore Pakistan Taibah University College of Computer Science and Engineering Medina42353 Saudi Arabia

ISBN: (纸本)9798350385144

The considerable surge in energy consumption due to population growth and the use of new technology has posed significant challenges to energy security and the environment. Managing energy consumption on the consumer side is crucial as the demand for energy continues to increase. Consumers need to monitor their daily usage and understand consumption standards to prepare themselves for energy efficiency and cost savings. To address these challenges, a Smart Energy Management System (SEMS) based on the Internet of Energy (IoE) has been developed. This system uses day-Ahead planning and accurate energy availability forecasting to manage energy demand in a smart environment with high sustainable energy penetration. The Fuzzy based Weighted Federated Learning (FWFML) approach is integrated into the system to optimize energy management. The SEMS system monitors energy usage at the user level, and a review of management plans has been introduced to improve energy efficiency in terms of 93.5% accuracy, and 6.5% miss-rate. This research work also highlights future challenges in developing SEMS to increase energy efficiency in a more robust manner. © 2024 IEEE.

关键词： Energy management systems

来源：评论

学校读者我要写书评

暂无评论

A Multi-Genre Urdu Broadcast Speech Recognition System

A Multi-Genre Urdu Broadcast Speech Recognition System

引用

Oriental COCOSDA International Conference on Speech Database and Assessments

作者： Erbaz Khan Sahar Rauf Farah Adeeba Sarmad Hussain Center for Language Engineering Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Lahore New Campus KSK. University of Engineering and Technology

ISBN: (纸本)9781665408714

This paper reports the development of a multi-genre Urdu Broadcast (BC) corpus and a Large Vocabulary Continuous Speech Recognition (LVCSR) system. BC speech corpus of 98 hours from 453 speakers is collected and annotated. For acoustic modeling, Time-delay Neural Network (TDNN) is developed with prior Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) training and alignments. For the language model, 3-gram, 4-gram and Recurrent Neural Network (RNN) based models are developed on a text corpus of 188 million words. The developed models are tested on 4.3 hours of unseen BC multi-genre speech dataset and the best Word Error Rate (WER) 18.59% is achieved using RNN based language Model (LM). Moreover, a detailed word error analysis is carried out to compare the errors made by humans and the Automatic Speech Recognition (ASR) System. The results showed a similar behavior of word misrecognitions by both humans and ASR.

关键词： Training Vocabulary Recurrent neural networks TV Error analysis System performance Perturbation methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing Large Vocabulary Continuous Speech Recognition System for Urdu-English Conversational Code-Switched Speech

Enhancing Large Vocabulary Continuous Speech Recognition Sys...

引用

Oriental COCOSDA International Conference on Speech Database and Assessments

作者： Muhammad Umar Farooq Farah Adeeba Sarmad Hussain Sahar Rauf Maryam Khalid Center for Language Engineering Al-Khawarizmi Institute of Computer Science University of Engineering and Technology Lahore

ISBN: (数字)9781728198965

ISBN: (纸本)9781728198972

This paper presents first step towards Large Vocabulary Continuous Speech Recognition (LVCSR) system for Urdu-English code-switched conversational speech. Urdu is the national language and lingua franca of Pakistan, with 100 million speakers worldwide. English, on the other hand, is official language of Pakistan and commonly mixed with Urdu in daily communication. Urdu, being under-resourced language, have no substantial Urdu-English code-switched corpus in hand to develop speech recognition system. In this research, readily available spontaneous Urdu speech corpus (25 hours) is revised to use it for enhancement of read speech Urdu LVCSR to recognize code-switched speech. This data set is split into 20 hours of train and 5 hours of test set. 10 hours of Urdu BroadCast (BC) data are collected and annotated in a semi-supervised way to enhance the system further. For acoustic modeling, state-of-the-art DNN-HMM modeling technique is used without any prior GMM-HMM training and alignments. Various techniques to improve language model using monolingual data are investigated. The overall percent Word Error Rate (WER) is reduced from 40.71% to 26.95% on test set.

关键词： Speech coding Speech recognition Speech enhancement Acoustics Data models Vocabulary Switches

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：