| |
Ms. Sahar Rauf works at CLE as an Assistant Manager Research. She has an M.Phil. in Applied Linguistics and around 8 years of research experience in Natural Language Processing (NLP). Her responsibilities include the management of a team of linguists that develop and annotate Urdu corpora for various projects. She is responsible for recording, sentence segmentation, phoneme level annotation, word boundary identification and labelling, stress marking, break index, and intonation level annotations for the development of the Urdu voice corpus. She has instructed Speech and Language Pathology students at the University of the Punjab on Acoustic Phonetics. She has also contributed to the sentiment analysis on Twitter data (English, Urdu, and Roman Urdu) for the projects titled, 'Hate Speech Detection', 'Epidemic Surveillance System', 'Aspect-based Political Sentiment Analysis' and 'Empowering Public Policy on Socio-Economic Issues through Citizens Sentiment Analysis'. She develops Urdu Lexicons for Text to Speech System (TTS) and Automatic Speech Recognition System (ASR). Currently, she is involved in the Broadcast data verification for the project titled, 'Automated Urdu Broadcast Media Content Extraction and Analytics' and also working on the development of Urdu Test Material for the Hearing-Impaired Community. Her research interests lie in the area of developing resources for local languages generally and developing Urdu Corpora specifically. |
|
