Papers by Brij Mohan Lal Srivastava
Phonetically Balanced Code-Mixed Speech Corpus for Hindi-English Automatic Speech Recognition (L18-1)
Copied to clipboard
Ayushi Pandey, Brij Mohan Lal Srivastava, Rohit Kumar, Bhanu Teja Nellore, Kasi Sai Teja, Suryakanth V. Gangashetty
| Challenge: | a phonetic balance in code-mixed Hindi-English corpus has been created . code-switching is a common phenomenon in multilingual and bilingual communities . |
| Approach: | They propose to create a phonetically balanced read speech corpus of code-mixed Hindi-English . they use a method to select sentences that contain triphones lower in frequency than a threshold . |
| Outcome: | The proposed corpus is phonetically balanced with a large code-mixed reference corpus. |
Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi (2020.lrec-1)
Copied to clipboard
Devansh Mehta, Sebastin Santy, Ramaravind Kommiya Mothilal, Brij Mohan Lal Srivastava, Alok Sharma, Anurag Shukla, Vishnu Prasad, Venkanna U, Amit Sharma, Kalika Bali
| Challenge: | 40% of all the languages in the world face the danger of extinction in the near future . when a language dies out, future generations lose a vital part of the culture that is necessary to completely understand it. |
| Approach: | They propose to use 4 technology-driven methods of data collection to collect data on Gondi, a low-resource vulnerable language spoken by 2.3 million tribal people in south and central India. |
| Outcome: | The proposed methods collected 12,000 translated words and/or sentences and identified more than 650 community members whose help can be solicited for future translation efforts. |