scholarly journals REDAT: Accent-Invariant Representation for End-To-End ASR by Domain Adversarial Training with Relabeling

2021 ◽  
Author(s):  
Hu Hu ◽  
Xuesong Yang ◽  
Zeynab Raeesy ◽  
Jinxi Guo ◽  
Gokce Keskin ◽  
...  
Keyword(s):  
Invariant Representation ◽  
Adversarial Training ◽  
End To End

scholarly journals Adversarial Deep Structural Networks for Mammographic Mass Segmentation

2016 ◽  
Author(s):  
Wentao Zhu ◽  
Xiaohui Xie
Keyword(s):  
Conditional Random Fields ◽  
Model Potential ◽  
Natural Image ◽  
Structural Learning ◽  
Mass Detection ◽  
Convolutional Network ◽  
Adversarial Training ◽  
Mass Segmentation ◽  
End To End ◽  
Public Datasets

AbstractMass segmentation is an important task in mammogram analysis, providing effective morphological features and regions of interest (ROI) for mass detection and classification. Inspired by the success of using deep convolutional features for natural image analysis and conditional random fields (CRF) for structural learning, we propose an end-to-end network for mammographic mass segmentation. The network employs a fully convolutional network (FCN) to model potential function, followed by a CRF to perform structural learning. Because the mass distribution varies greatly with pixel position, the FCN is combined with position priori for the task. Due to the small size of mammogram datasets, we use adversarial training to control over-fitting. Four models with different convolutional kernels are further fused to improve the segmentation results. Experimental results on two public datasets, INbreast and DDSM-BCRP, show that our end-to-end network combined with adversarial training achieves the-state-of-the-art results.

scholarly journals Accented Speech Recognition Based on End-to-End Domain Adversarial Training of Neural Networks

2021 ◽  
Vol 11 (18) ◽  
pp. 8412
Author(s):  
Hyeong-Ju Na ◽  
Jeong-Sik Park
Keyword(s):  
Speech Recognition ◽  
Domain Adaptation ◽  
Training Data ◽  
Baseline Model ◽  
Linguistic Differences ◽  
Computational Costs ◽  
Accented Speech ◽  
Feature Extractor ◽  
Adversarial Training ◽  
End To End

The performance of automatic speech recognition (ASR) may be degraded when accented speech is recognized because the speech has some linguistic differences from standard speech. Conventional accented speech recognition studies have utilized the accent embedding method, in which the accent embedding features are directly fed into the ASR network. Although the method improves the performance of accented speech recognition, it has some restrictions, such as increasing the computational costs. This study proposes an efficient method of training the ASR model for accented speech in a domain adversarial way based on the Domain Adversarial Neural Network (DANN). The DANN plays a role as a domain adaptation in which the training data and test data have different distributions. Thus, our approach is expected to construct a reliable ASR model for accented speech by reducing the distribution differences between accented speech and standard speech. DANN has three sub-networks: the feature extractor, the domain classifier, and the label predictor. To adjust the DANN for accented speech recognition, we constructed these three sub-networks independently, considering the characteristics of accented speech. In particular, we used an end-to-end framework based on Connectionist Temporal Classification (CTC) to develop the label predictor, a very important module that directly affects ASR results. To verify the efficiency of the proposed approach, we conducted several experiments of accented speech recognition for four English accents including Australian, Canadian, British (England), and Indian accents. The experimental results showed that the proposed DANN-based model outperformed the baseline model for all accents, indicating that the end-to-end domain adversarial training effectively reduced the distribution differences between accented speech and standard speech.

scholarly journals End-to-End Speech Translation with Adversarial Training

2020 ◽  
Author(s):  
Xuancai Li ◽  
Chen Kehai ◽  
Tiejun Zhao ◽  
Muyun Yang
Keyword(s):  
Speech Translation ◽  
Adversarial Training ◽  
End To End

Adversarial training and decoding strategies for end-to-end neural conversation models

2019 ◽  
Vol 54 ◽  
pp. 122-139 ◽  
Author(s):  
Takaaki Hori ◽  
Wen Wang ◽  
Yusuke Koji ◽  
Chiori Hori ◽  
Bret Harsham ◽  
...  
Keyword(s):  
Adversarial Training ◽  
End To End

Surgical management of extracranial carotid artery aneurysms

VASA ◽  
2016 ◽  
Vol 45 (3) ◽  
pp. 223-228 ◽  
Author(s):  
Jan Paweł Skóra ◽  
Jacek Kurcz ◽  
Krzysztof Korta ◽  
Przemysław Szyber ◽  
Tadeusz Andrzej Dorobisz ◽  
...  
Keyword(s):  
Carotid Artery ◽  
Surgical Management ◽  
Minor Stroke ◽  
Stroke Rate ◽  
Extracranial Carotid Artery ◽  
Long Term Follow Up ◽  
End To End ◽  
Dacron Patch ◽  
Major Stroke

Abstract. Background: We present the methods and results of the surgical management of extracranial carotid artery aneurysms (ECCA). Postoperative complications including early and late neurological events were analysed. Correlation between reconstruction techniques and morphology of ECCA was assessed in this retrospective study. Patients and methods: In total, 32 reconstructions of ECCA were performed in 31 symptomatic patients with a mean age of 59.2 (range 33 - 84) years. The causes of ECCA were divided among atherosclerosis (n = 25; 78.1 %), previous carotid endarterectomy with Dacron patch (n = 4; 12.5 %), iatrogenic injury (n = 2; 6.3 %) and infection (n = 1; 3.1 %). In 23 cases, intervention consisted of carotid bypass. Aneurysmectomy with end-to-end suture was performed in 4 cases. Aneurysmal resection with patching was done in 2 cases and aneurysmorrhaphy without patching in another 2 cases. In 1 case, ligature of the internal carotid artery (ICA) was required. Results: Technical success defined as the preservation of ICA patency was achieved in 31 cases (96.9 %). There was one perioperative death due to major stroke (3.1 %). Two cases of minor stroke occurred in the 30-day observation period (6.3 %). Three patients had a transient hypoglossal nerve palsy that subsided spontaneously (9.4 %). At a mean long-term follow-up of 68 months, there were no major or minor ipsilateral strokes or surgery-related deaths reported. In all 30 surviving patients (96.9 %), long-term clinical outcomes were free from ipsilateral neurological symptoms. Conclusions: Open surgery is a relatively safe method in the therapy of ECCA. Surgical repair of ECCAs can be associated with an acceptable major stroke rate and moderate minor stroke rate. Complication-free long-term outcomes can be achieved in as many as 96.9 % of patients. Aneurysmectomy with end-to-end anastomosis or bypass surgery can be implemented during open repair of ECCA.

Reliability of the Mangled Extremity Severity Score in the Management of Peripheral Vascular Injuries in Children: A Retrospective Review

2020 ◽  
Author(s):  
Ahmed Mousa ◽  
Ossama M. Zakaria ◽  
Mai A. Elkalla ◽  
Lotfy A. Abdelsattar ◽  
Hamad Al-Game'a
Keyword(s):  
Severity Score ◽  
Vein Graft ◽  
Bypass Surgery ◽  
Age Groups ◽  
Vascular Injuries ◽  
Peripheral Vascular ◽  
Group Iii ◽  
Mangled Extremity ◽  
Group I ◽  
End To End

AbstractThis study was aimed to evaluate different management modalities for peripheral vascular trauma in children, with the aid of the Mangled Extremity Severity Score (MESS). A single-center retrospective analysis took place between 2010 and 2017 at University Hospitals, having emergencies and critical care centers. Different types of vascular repair were adopted by skillful vascular experts and highly trained pediatric surgeons. Patients were divided into three different age groups. Group I included those children between 5 and 10 years; group II involved pediatrics between 11 and 15 years; while children between 16 and 21 years participated in group III. We recruited 183 children with peripheral vascular injuries. They were 87% males and 13% females, with the mean age of 14.72 ± 04. Arteriorrhaphy was performed in 32%; end-to-end anastomosis and natural vein graft were adopted in 40.5 and 49%, respectively. On the other hand, 10.5% underwent bypass surgery. The age groups I and II are highly susceptible to penetrating trauma (p = 0.001), while patients with an extreme age (i.e., group III) are more susceptible to blunt injury (p = 0.001). The MESS has a significant correlation to both age groups I and II (p = 0.001). Vein patch angioplasty and end-to-end primary repair should be adopted as the main treatment options for the repair of extremity vascular injuries in children. Moreover, other treatment modalities, such as repair with autologous vein graft/bypass surgery, may be adopted whenever possible. They are cost-effective, reliable, and simple techniques with fewer postoperative complication, especially in poor/limited resources.

WS-Security on PRODML

2014 ◽  
Vol 1 (1) ◽  
pp. 9-34
Author(s):  
Bobby Suryajaya
Keyword(s):  
Web Services ◽  
Digital Signature ◽  
Data Transfer ◽  
Web Services Security ◽  
Soap Message ◽  
Simulation Results ◽  
End To End

SKK Migas plans to apply end-to-end security based on Web Services Security (WS-Security) for Sistem Operasi Terpadu (SOT). However, there are no prototype or simulation results that can support the plan that has already been communicated to many parties. This paper proposes an experiment that performs PRODML data transfer using WS-Security by altering the WSDL to include encryption and digital signature. The experiment utilizes SoapUI, and successfully loaded PRODML WSDL that had been altered with WSP-Policy based on X.509 to transfer a SOAP message.

Sign in / Sign up

Export Citation Format

Share Document