Search Results for author:
Found 8 papers, 3 papers with code
Post-training Model Quantization Using GANs for Synthetic Data Generation
In this study, we investigate the use of synthetic data as a substitute for the calibration with real data for the quantization method.
STC speaker recognition systems for the NIST SRE 2021
This paper presents a description of STC Ltd. systems submitted to the NIST 2021 Speaker Recognition Evaluation for both fixed and open training conditions.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Post-training deep neural network pruning via layer-wise calibration
We present a post-training weight pruning method for deep neural networks that achieves accuracy levels tolerable for the production setting and that is sufficiently fast to be run on commodity hardware such as desktop CPUs or edge devices.
Neural Network Compression Framework for fast model inference
In this work we present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF).
Ranked #3 on
Binarization
on ImageNet
Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances
Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets.
Lightweight Network Architecture for Real-Time Action Recognition
We conduct a comparison with state-of-the-art methods and show that our approach performs on par with most of them on famous Action Recognition datasets.
Development of Real-time ADAS Object Detector for Deployment on CPU
In this work, we outline the set of problems, which any Object Detection CNN faces when its development comes to the deployment stage and propose methods to deal with such difficulties.
Audio-replay attack detection countermeasures
This paper presents the Speech Technology Center (STC) replay attack detection systems proposed for Automatic Speaker Verification Spoofing and Countermeasures Challenge 2017.
