INT8 Winograd Acceleration for Conv1D Equipped ASR Models Deployed on Mobile Devices

by   Yiwu Yao, et al.

The intensive computation of Automatic Speech Recognition (ASR) models obstructs them from being deployed on mobile devices. In this paper, we present a novel quantized Winograd optimization pipeline, which combines the quantization and fast convolution to achieve efficient inference acceleration on mobile devices for ASR models. To avoid the information loss due to the combination of quantization and Winograd convolution, a Range-Scaled Quantization (RSQ) training method is proposed to expand the quantized numerical range and to distill knowledge from high-precision values. Moreover, an improved Conv1D equipped DFSMN (ConvDFSMN) model is designed for mobile deployment. We conduct extensive experiments on both ConvDFSMN and Wav2letter models. Results demonstrate the models can be effectively optimized with the proposed pipeline. Especially, Wav2letter achieves 1.48* speedup with an approximate 0.07



There are no comments yet.


page 1

page 2

page 3

page 4


AutoQB: AutoML for Network Quantization and Binarization on Mobile Devices

In this paper, we propose a hierarchical deep reinforcement learning (DR...

HASP: A High-Performance Adaptive Mobile Security Enhancement Against Malicious Speech Recognition

Nowadays, machine learning based Automatic Speech Recognition (ASR) tech...

RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition

Recurrent neural networks (RNNs) based automatic speech recognition has ...

MobiVSR: A Visual Speech Recognition Solution for Mobile Devices

Visual speech recognition (VSR) is the task of recognizing spoken langua...

A Quantization-Friendly Separable Convolution for MobileNets

As deep learning (DL) is being rapidly pushed to edge computing, researc...

Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition

End-to-end neural network models achieve improved performance on various...

Training and Profiling a Pediatric Emotion Recognition Classifier on Mobile Devices

Implementing automated emotion recognition on mobile devices could provi...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.