research
∙
08/18/2023
Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization
The task of lip synchronization (lip-sync) seeks to match the lips of hu...
share
research
∙
12/16/2021
Domain Prompts: Towards memory and compute efficient domain adaptation of ASR systems
Automatic Speech Recognition (ASR) systems have found their use in numer...
research
∙
10/13/2021
Efficient domain adaptation of language models in ASR systems using Prompt-tuning
Automatic Speech Recognition (ASR) systems have found their use in numer...
research
∙
07/30/2021
Towards Continual Entity Learning in Language Models for Conversational Agents
Neural language models (LM) trained on diverse corpora are known to work...
research
∙
07/10/2020
Neural Composition: Learning to Generate from Multiple Models
Decomposing models into multiple components is critically important in m...
research
∙
04/05/2019