Follow
Shreekantha Nadig
Shreekantha Nadig
End-to-end ASR at Dialpad
Verified email at iiitb.ac.in - Homepage
Title
Cited by
Cited by
Year
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
62020
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
42021
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
22020
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
22020
Double Decoder: Improving latency for Streaming End-to-end ASR Models
R Wang, S Nadig, D Kulko, S Vandieken, CT Chang, SS Sarfjoo, ...
Proceedings of the 7th International Conference on Natural Language and …, 2024
2024
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
The system can't perform the operation now. Try again later.
Articles 1–6