Publications/Speech Processing, Recognition & Audio Security
Conference · 2010
An ASR System for Spontaneous Urdu Speech
Agha Ali Raza, Sarmad Hussain, Huda Sarfraz, Inam Ullah, Zahid Sarfraz
Oriental COCOSDA 2010, Kathmandu, Nepal
Summary
Recognizing spontaneous, everyday speech is hard partly because transcribed spontaneous recordings are scarce, while transcribed read speech is comparatively easy to obtain. This paper asks whether a recognizer for spontaneous speech can be trained on a mixture of read and spontaneous data, and reports a single-speaker, medium-vocabulary recognition system for spontaneous Urdu, an early step toward speech technology for the language.
Cite this paper
Agha Ali Raza, Sarmad Hussain, Huda Sarfraz, Inam Ullah, Zahid Sarfraz. An ASR System for Spontaneous Urdu Speech. Oriental COCOSDA 2010, Kathmandu, Nepal.
@inproceedings{raza2010asr,
author = {Agha Ali Raza and Sarmad Hussain and Huda Sarfraz and Inam Ullah and Zahid Sarfraz},
title = {{An ASR System for Spontaneous Urdu Speech}},
booktitle = {Oriental COCOSDA 2010, Kathmandu, Nepal},
year = {2010},
url = {https://aghaaliraza.com/publications/2010--O-COCOSDA--An_ASR_System_for_Spontaneous_Urdu_Speech.pdf}
}
- Dissecting ASR Failures in Low-Resource South Asian LanguagesInterspeech 2026, Sydney, Australia
- WER We Stand: Benchmarking Urdu ASR ModelsCOLING 2025, Abu Dhabi, UAE
- Conversations in the Wild: Data Collection, Automatic Generation and EvaluationComputer Speech & Language, vol. 89, 2025
- Deepfake Defense: Constructing and Evaluating a Specialized Urdu Deepfake Audio DatasetFindings of ACL 2024, Bangkok, Thailand
- Speech Emotion Recognition for the Urdu LanguageLanguage Resources and Evaluation (LRE), 2023