4 papers
Compute Cost Amortized Transformer for Streaming ASR
Yi Xie, Jonathan Macoskey, Martin Radfar +5
We present a streaming, Transformer-based end-to-end automatic speech recognition (ASR) architecture which achieves efficient neural inference through compute cost amortization. Ou…
Learning a Neural Diff for Speech Models
Jonathan Macoskey, Grant P. Strimel, Ariya Rastrow
As more speech processing applications execute locally on edge devices, a set of resource constraints must be considered. In this work we address one of these constraints, namely o…
Bifocal Neural ASR: Exploiting Keyword Spotting for Inference Optimization
Jonathan Macoskey, Grant P. Strimel, Ariya Rastrow
We present Bifocal RNN-T, a new variant of the Recurrent Neural Network Transducer (RNN-T) architecture designed for improved inference time latency on speech recognition tasks. Th…
Amortized Neural Networks for Low-Latency Speech Recognition
Jonathan Macoskey, Grant P. Strimel, Jinru Su +1
We introduce Amortized Neural Networks (AmNets), a compute cost- and latency-aware network architecture particularly well-suited for sequence modeling tasks. We apply AmNets to the…