Header

UZH-Logo

Maintenance Infos

Impact of low-precision deep regression networks on single-channel source separation


Ceolini, Enea; Liu, Shih-Chii (2017). Impact of low-precision deep regression networks on single-channel source separation. In: The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP2017, New Orleans LA, USA, 5 March 2017 - 9 March 2017.

Abstract

Recent work on developing training methods for reduced precision Deep Convolutional Networks show that these networks can perform with similar accuracy to full precision networks when tested on a classification task. Reduced precision networks decrease the demand on the memory and computational power capabilities of the computing platform. This paper investigates the impact of reduced precision deep Recurrent Neural Networks (RNNs) when trained on a regression task, in this case, a monaural source separation task. The effect of reduced precision nets is explored for two popular recurrent network architectures: Vanilla RNNs and RNNs using Long-Short Term Memory (LSTM) units. The results show that the performance of the networks as measured by blind source separation metrics and speech intelligibility tests on two datasets, show very little decrease even when the weight precision goes down to 4 bits.

Abstract

Recent work on developing training methods for reduced precision Deep Convolutional Networks show that these networks can perform with similar accuracy to full precision networks when tested on a classification task. Reduced precision networks decrease the demand on the memory and computational power capabilities of the computing platform. This paper investigates the impact of reduced precision deep Recurrent Neural Networks (RNNs) when trained on a regression task, in this case, a monaural source separation task. The effect of reduced precision nets is explored for two popular recurrent network architectures: Vanilla RNNs and RNNs using Long-Short Term Memory (LSTM) units. The results show that the performance of the networks as measured by blind source separation metrics and speech intelligibility tests on two datasets, show very little decrease even when the weight precision goes down to 4 bits.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

0 downloads since deposited on 23 Feb 2018
0 downloads since 12 months

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Language:English
Event End Date:9 March 2017
Deposited On:23 Feb 2018 09:42
Last Modified:31 Jul 2018 05:11
Publisher:Acoustics, Speech and Signal Processing (ICASSP), 2017 IEEE International Conference on
Series Name:IEEE Internal Conference on Acoustics, Speech, and Signal Processing (ICASSP)
OA Status:Closed
Free access at:Official URL. An embargo period may apply.
Publisher DOI:https://doi.org/10.1109/ICASSP.2017.7952157
Official URL:http://ieeexplore.ieee.org/document/7952157/

Download