AIConfPaper
← Search

Devang Kulshreshtha

2 accepted papers

2023

Mask the Bias: Improving Domain-Adaptive Generalization of CTC-Based ASR with Internal Language Model Estimation

Nilaksh Das, Monica Sunkara, Sravan Bodapati, Jinglun Cai, Devang Kulshreshtha, Jeff Farris +1
ICASSP 2023accepted

End-to-end ASR models trained on large amount of data tend to be implicitly biased towards language semantics of the training data. Internal language model estimation (ILME) has been proposed to mitigate this bias for autoregressive models such as attention-based encoder-decoder and RNN-T. Typically…

Cited by 0Source ↗Scholar ↗
2021

Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval

Devang Kulshreshtha, Robert Belfer, Iulian Vlad Serban, Siva Reddy
EMNLP 2021main

In this work, we introduce back-training, an alternative to self-training for unsupervised domain adaptation (UDA). While self-training generates synthetic training data where natural inputs are aligned with noisy outputs, back-training results in natural outputs aligned with noisy inputs. This sign…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗