WhisperPipe delivers 89 ms median latency and 48% lower peak GPU memory than standard Whisper while keeping word error rate within 2% of the offline model.
Streaming End-to-End Speech Recognition with Transformer Transducer
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
A temporal spectral noise-floor adaptation algorithm enables reliable event triggering in IoT mesh networks by suppressing nuisance triggers from environmental non-stationarity while preserving sensitivity to true signals.
citing papers explorer
-
WhisperPipe: A Resource-Efficient Streaming Architecture for Real-Time Automatic Speech Recognition
WhisperPipe delivers 89 ms median latency and 48% lower peak GPU memory than standard Whisper while keeping word error rate within 2% of the offline model.
-
Temporal Spectral Noise-Floor Adaptation for Error-Intolerant Trigger Integrity in IoT Mesh Networks
A temporal spectral noise-floor adaptation algorithm enables reliable event triggering in IoT mesh networks by suppressing nuisance triggers from environmental non-stationarity while preserving sensitivity to true signals.