4 citations · 9 across the 6 of their papers we have counts for
6 papers
The Majority Vote Paradigm Shift: When Popular Meets Optimal
Antonio Purificato, Maria Sofia Bucarelli, Anil Kumar Nelakanti +3
Reliably labelling data typically requires annotations from multiple human workers. However, humans are far from being perfect. Hence, it is a common practice to aggregate labels g…
ParrotTTS: Text-to-Speech synthesis by exploiting self-supervised representations
Neil Shah, Saiteja Kosgi, Vishal Tambrahalli +3
We present ParrotTTS, a modularized text-to-speech synthesis model leveraging disentangled self-supervised speech representations. It can train a multi-speaker variant effectively…
Detecting over/under-translation errors for determining adequacy in human translations
Prabhakar Gupta, Ridha Juneja, Anil Nelakanti +1
We present a novel approach to detecting over and under translations (OT/UT) as part of adequacy error checks in translation evaluation. We do not restrict ourselves to machine tra…
DeepSubQE: Quality estimation for subtitle translations
Prabhakar Gupta, Anil Nelakanti
Quality estimation (QE) for tasks involving language data is hard owing to numerous aspects of natural language like variations in paraphrasing, style, grammar, etc. There can be m…
Object-Level Context Modeling For Scene Classification with Context-CNN
Syed Ashar Javed, Anil Kumar Nelakanti
Convolutional Neural Networks (CNNs) have been used extensively for computer vision tasks and produce rich feature representation for objects or parts of an image. But reasoning ab…
Responding to Retrieval: A Proposal to Use Retrieval Information for Better Presentation of Website Content
C Ravindranath Chowdary, Anil Kumar Singh, Anil Nelakanti
Retrieval and content management are assumed to be mutually exclusive. In this paper we suggest that they need not be so. In the usual information retrieval scenario, some informat…