research
∙
05/10/2023
Post-training Model Quantization Using GANs for Synthetic Data Generation
Quantization is a widely adopted technique for deep neural networks to r...
share
research
∙
12/20/2021
Enabling NAS with Automated Super-Network Generation
Recent Neural Architecture Search (NAS) solutions have produced impressi...
research
∙
11/03/2021
STC speaker recognition systems for the NIST SRE 2021
This paper presents a description of STC Ltd. systems submitted to the N...
research
∙
04/30/2021
Post-training deep neural network pruning via layer-wise calibration
We present a post-training weight pruning method for deep neural network...
research
∙
02/20/2020
Neural Network Compression Framework for fast model inference
In this work we present a new framework for neural networks compression ...
research
∙
02/14/2020
Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances
Speaker recognition systems based on deep speaker embeddings have achiev...
research
∙
05/21/2019
Lightweight Network Architecture for Real-Time Action Recognition
In this work we present a new efficient approach to Human Action Recogni...
research
∙
11/14/2018
Development of Real-time ADAS Object Detector for Deployment on CPU
In this work, we outline the set of problems, which any Object Detection...
research
∙
05/24/2017