metadata

license: apache-2.0
datasets:
  - VoiceBank+DEMAND
tags:
  - ENOT-AutoDL
  - SpeechEnhancement

ENOT-AutoDL MP-SENet optimization on VoiceBank+DEMAND dataset.

This repository contains the optimized version of MP-SENet model. Number of MACs aka FLOPS was used for computational complexity measurement. PESQ score was used as a quality metric.

Optimization results

We use MACs as a latency measure because this metric is device-agnostic and implementation independent.
There is also a possibility to optimize a model by target device latency using ENOT neural architecture selection algorithm.
Please, keep in mind that acceleration by device latency differs from acceleration by MACs.

Model	MACs	acceleration	PESQ score
baseline	302.39 B	1.0	3.381
ENOT optimized	120.95 B	2.5	3.386

If you want to book a demo, please contact us: enot@enot.ai .