2 papers
cs.SD2021
One TTS Alignment To Rule Them All
Rohan Badlani, Adrian Łancucki, Kevin J. Shih +3
Speech-to-text alignment is a critical component of neural textto-speech (TTS) models. Autoregressive TTS models typically use an attention mechanism to learn these alignments on-l…
cs.CL2020
Relation Extraction with Contextualized Relation Embedding (CRE)
Xiaoyu Chen, Rohan Badlani
Relation extraction is the task of identifying relation instance between two entities given a corpus whereas Knowledge base modeling is the task of representing a knowledge base, i…