Compute Cost Amortized Transformer for Streaming ASR

no code implementations • 5 Jul 2022 • Yi Xie, Jonathan Macoskey, Martin Radfar, Feng-Ju Chang, Brian King, Ariya Rastrow, Athanasios Mouchtaris, Grant P. Strimel

We present a streaming, Transformer-based end-to-end automatic speech recognition (ASR) architecture which achieves efficient neural inference through compute cost amortization.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Bifocal Neural ASR: Exploiting Keyword Spotting for Inference Optimization

no code implementations • 3 Aug 2021 • 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.

Inference Optimization Keyword Spotting +3

Learning a Neural Diff for Speech Models

no code implementations • 3 Aug 2021 • 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.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Amortized Neural Networks for Low-Latency Speech Recognition

no code implementations • 3 Aug 2021 • Jonathan Macoskey, Grant P. Strimel, Jinru Su, Ariya Rastrow

We apply AmNets to the Recurrent Neural Network Transducer (RNN-T) to reduce compute cost and latency for an automatic speech recognition (ASR) task.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1