TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids

05/20/2020
by   Igor Fedorov, et al.
0

Modern speech enhancement algorithms achieve remarkable noise suppression by means of large recurrent neural networks (RNNs). However, large RNNs limit practical deployment in hearing aid hardware (HW) form-factors, which are battery powered and run on resource-constrained microcontroller units (MCUs) with limited memory capacity and compute capability. In this work, we use model compression techniques to bridge this gap. We define the constraints imposed on the RNN by the HW and describe a method to satisfy them. Although model compression techniques are an active area of research, we are the first to demonstrate their efficacy for RNN speech enhancement, using pruning and integer quantization of weights/activations. We also demonstrate state update skipping, which reduces the computational load. Finally, we conduct a perceptual evaluation of the compressed models to verify audio quality on human raters. Results show a reduction in model size and operations of 11.9× and 2.9×, respectively, over the baseline for compressed models, without a statistical difference in listening preference and only exhibiting a loss of 0.55dB SDR. Our model achieves a computational latency of 2.39ms, well within the 10ms target and 351× better than previous work.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/22/2022

Inference skipping for more efficient real-time speech enhancement with parallel RNNs

Deep neural network (DNN) based speech enhancement models have attracted...
research
05/26/2021

Self-attending RNN for Speech Enhancement to Improve Cross-corpus Generalization

Deep neural networks (DNNs) represent the mainstream methodology for sup...
research
11/03/2021

Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators

We explore network sparsification strategies with the aim of compressing...
research
02/16/2018

Constrained Convolutional-Recurrent Networks to Improve Speech Quality with Low Impact on Recognition Accuracy

For a speech-enhancement algorithm, it is highly desirable to simultaneo...
research
07/12/2021

DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement

The dual-path RNN (DPRNN) was proposed to more effectively model extreme...
research
10/14/2022

Accelerating RNN-based Speech Enhancement on a Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantization

This paper presents an optimized methodology to design and deploy Speech...
research
06/12/2019

Run-Time Efficient RNN Compression for Inference on Edge Devices

Recurrent neural networks can be large and compute-intensive, yet many a...

Please sign up or login with your details

Forgot password? Click here to reset