SANBAR@LT-EDI-2023:Automatic Speech Recognition: vulnerable old-aged and transgender people in Tamil
Abstract
An Automatic Speech Recognition systems for Tamil are designed to convert spoken lan- guage or speech signals into written Tamil text. Seniors go to banks, clinics and authoritative workplaces to address their regular necessities. A lot of older people are not aware of the use of the facilities available in public places or office. They need a person to help them. Like- wise, transgender people are deprived of pri- mary education because of social stigma, so speaking is the only way to help them meet their needs. In order to build speech enabled systems, spontaneous speech data is collected from seniors and transgender people who are deprived of using these facilities for their own benefit. The proposed system is developed with pretraind models are IIT Madras transformer ASR model and akashsivanandan/wav2vec2- large-xls-r-300m-tamil model. Both pretrained models are used to evaluate the test speech ut- terances, and obtainted the WER as 37.7144% and 40.55% respectively.- Anthology ID:
- 2023.ltedi-1.23
- Volume:
- Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion
- Month:
- September
- Year:
- 2023
- Address:
- Varna, Bulgaria
- Editors:
- Bharathi R. Chakravarthi, B. Bharathi, Joephine Griffith, Kalika Bali, Paul Buitelaar
- Venues:
- LTEDI | WS
- SIG:
- Publisher:
- INCOMA Ltd., Shoumen, Bulgaria
- Note:
- Pages:
- 155–160
- Language:
- URL:
- https://aclanthology.org/2023.ltedi-1.23
- DOI:
- Cite (ACL):
- Saranya S and Bharathi B. 2023. SANBAR@LT-EDI-2023:Automatic Speech Recognition: vulnerable old-aged and transgender people in Tamil. In Proceedings of the Third Workshop on Language Technology for Equality, Diversity and Inclusion, pages 155–160, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
- Cite (Informal):
- SANBAR@LT-EDI-2023:Automatic Speech Recognition: vulnerable old-aged and transgender people in Tamil (S & B, LTEDI-WS 2023)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2023.ltedi-1.23.pdf