| Multi-target hybrid CTC-Attentional Decoder for joint phoneme-grapheme recognition S Nadig, V Ramasubramanian, S Rao 2020 International Conference on Signal Processing and Communications (SPCOM …, 2020 | 6 | 2020 |
| Avengers, Ensemble! Benefits of ensembling in grapheme-to-phoneme prediction V Gautam, WY Li, Z Mahmood, F Mailhot, S Nadig, R Wang, N Zhang Proceedings of the 18th SIGMORPHON Workshop on Computational Research in …, 2021 | 4 | 2021 |
| Jointly learning to align and transcribe using attention-based alignment and uncertainty-to-weigh losses S Nadig, S Chakraborty, A Shah, C Sharma, V Ramasubramanian, S Rao 2020 International Conference on Signal Processing and Communications (SPCOM …, 2020 | 2 | 2020 |
| Semi-supervised learning for acoustic model retraining: Handling speech data with noisy transcript A Madan, A Khopkar, S Nadig, KMS Raghavan, D Eledath, ... 2020 International Conference on Signal Processing and Communications (SPCOM …, 2020 | 2 | 2020 |
| N-gram Boosting: Improving Contextual Biasing with Normalized N-gram Targets WY Li, S Nadig, K Chang, Z Mahmood, R Wang, S Vandieken, ... arXiv preprint arXiv:2308.02092, 2023 | | 2023 |
| N-gram Boosting: Improving Contextual Biasing with Normalized N-gram Targets FM Wang Yau Li, Shreekantha Nadig, Karol Chang, Zafarullah Mahmood, Riqiang ... https://arxiv.org/abs/2308.02092, 2023 | | 2023 |
V RamasubramanianProfessor, International Institute of Information Technology, Bangalore (IIIT-B)在 iiitb.ac.in 的电子邮件经过验证
