Amit Meghanani

Department of Computer Science

The University of Sheffield, UK

I am a PhD student at UKRI CDT in Speech and Language Technologies under the supervision of Prof. Thomas Hain , University of Sheffield. I am also a member of SPandH and Machine Intelligence for Natural Interfaces (MINI) research group. Currently, I am working on self-supervised learning for speech, disentangled speech representations, cost-effective self-supervised fine-tuning of self-supervised learning based speech models for task-specific speech representations. Acoustic word/sub-word embeddings.

Before joining my PhD, I worked as a senior data scientist at Publicis Sapient. Before that, I did my M.Tech (Research) from the Dept. of Electrical Engineering Indian Institute of Science (IISc), Bangalore, working for Medical Intelligence and Language Engineering (MILE) lab under the supervision of Prof. A. G. Ramakrishnan. I was a project assoicate at the same lab after finishing my masters for 3 months. During my term at IISc, I have worked on various research topics like speaker recognition, speech recognition, natural language processing for social media , applied machine and deep learning for recognising cognitive impairments using clinical data, etc.

news

Apr 16, 2024	Poster presentation of the paper ‘‘SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations’’ at ICASSP 2024!
Mar 18, 2024	Oral presentation of the paper ‘‘Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representations’’ at EACL 2024 Main confrerence !
Jan 18, 2024	Recent work “Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representations” has been accepted at EACL 2024 Main Conference.
Dec 17, 2023	Presented poster ‘‘Deriving Translational Acoustic Sub-word Embeddings’’ at ASRU 2023
Dec 13, 2023	Recent work “SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations” has been accepted at ICASSP 2024.