RelateLM uses transliteration to convert the unseen script of limited LRL text into the script of a Related Prominent Language (RPL) (Hindi in our case).
Towards easily customizable KWS models, we present KeySEM (Keyword Speech EMbedding), a speech embedding model pre-trained on the task of recognizing a large number of keywords.
We consider the task of personalizing ASR models while being constrained by a fixed budget on recording speaker-specific utterances.
We evaluate named entity representations of BERT-based NLP models by investigating their robustness to replacements from the same typed class in the input.
Accordingly, we propose a novel coupling of an open-source accent-tuned local model with the black-box service where the output from the service guides frame-level inference in the local model.
Empirical evaluation on five different tasks shows that (1) our algorithm is more accurate than several existing methods of learning from a mix of clean and noisy supervision, and (2) the coupled rule-exemplar supervision is effective in denoising rules.
We present a Parallel Iterative Edit (PIE) model for the problem of local sequence transduction arising in tasks like Grammatical error correction (GEC).