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.CL2023
Personalized Predictive ASR for Latency Reduction in Voice Assistants
Andreas Schwarz, Di He, Maarten Van Segbroeck +2
Streaming Automatic Speech Recognition (ASR) in voice assistants can utilize prefetching to partially hide the latency of response generation. Prefetching involves passing a prelim…