Showing cs.CLShow all
2 papers · 1 filter
cs.CL2024
Promptformer: Prompted Conformer Transducer for ASR
Sergio Duarte-Torres, Arunasish Sen, Aman Rana +5
Context cues carry information which can improve multi-turn interactions in automatic speech recognition (ASR) systems. In this paper, we introduce a novel mechanism inspired by hy…
cs.CL2022
Unified Modeling of Multi-Domain Multi-Device ASR Systems
Soumyajit Mitra, Swayambhu Nath Ray, Bharat Padi +6
Modern Automatic Speech Recognition (ASR) systems often use a portfolio of domain-specific models in order to get high accuracy for distinct user utterance types across different d…