0% Complete
صفحه اصلی
/
بیست و نهمین کنفرانس مهندسی برق ایران
Attractors Manipulation in Denoising Autoencoders for Robust Phone Recognition
نویسندگان :
Shaghayegh Reza
1
Seyyed Ali Seyyedsalehi
2
Seyyedeh Zohreh Seyyedsalehi
3
1- دانشگاه صنعتی امیرکبیر
2- دانشگاه صنعتی امیرکبیر
3- دانشگاه صنعتی امیرکبیر
کلمات کلیدی :
deep neural networks, denoising autoencoders, attractors, acoustic landmarks, robust recognition, phone recognition
چکیده :
Autoencoder Neural Networks are capable to filter out unwanted variabilities; however, their performance will degrade if their attractors and their basins of attraction are not properly adjusted. In this paper a heuristic method is proposed to increase the number of attractors shaped in desired points and expand their basins of attraction. These well-formed attractors can compensate unwanted variabilities and hence increase the chance of robust recognition. The effectiveness of this method is shown on synthetic data and is compared with another attractor manipulation method called cyclic method. In addition, the performance of this method on phone recognition task has shown 22.1 percent relative increase in the number of attractors and 4.2 percent relative improvement in the phone error rate on Farsdat database.
لیست مقالات
لیست مقالات بایگانی شده
{High performance detector for massive MIMO systems using an adaptive filering approach
Masoud Tahmasbi Fard - Mojtaba Amiri - Ali Olfat
ارائه ساختار پیشنهادی ترانسفورماتور حالت جامد یک سویه در بهره برداری از شبکه های توزیع
بهنام بهارلوئی - رضا قندهاری - مهدی بابایی - یوسف عطائی
Estimation of the Arc Model Parameters Using Heuristic Optimization Methods
Sadegh Ghavami - Ali A Razi-kazemi
Application of Artificial Neural Network on Diagnosing Location and Extent of Disk Space Variations in Transformer Windings Using Frequency Response Analysis
Reza Behkam - Hossein Karami - Mahdi Salay Naderi - Gevork Gharehpetian
High Performance and Low Power Spintronic Binarized Neural Network Hardware Accelerator
Milad Tanavardi Nasab - Arefe Amirany - Mohammad Hossein Moaiyeri - Kian Jafari
MAD-TI: Meta-path Aggregated-Graph Attention Network for Drug Target Interaction Prediction
Reza Shami Tanha - Maryam Sadighian - Arash Zabihian - Mohsen Hooshmand - Mohsen Afsharchi
Fully Soft-Switched Quadratic High Step-Up DC-DC Converter with a Single Switch and Low Input Current Ripple for Renewable Energy Applications
Ali Nadermohammadi - Hamed Abdi - Pouya Abolhassani - Seyed Hossein Hosseini - Mehran Sabahi - Naghi Rostami
A straightforward approach for measuring blood pressure in an upper arm digital blood pressure monitor
Mohammad Soroush Rezaei - Mahdi Khalilzadeh Shabestari - Seyed Yousef Jazaery Farsany - Danial Katoozian - Hossein Hosseini-Nejad
Optimal Placement of Of Maintenance Teams in Distribution Networks to Minimize Energy Not Supplied
Qasem Asadi - Ali Ashoornezhad - Hamid Falaghi - Maryam Ramezani
Forged Channel: A Breakthrough Approach for Accurate Parkinson's Disease Classification using Leave-One-Subject-Out Cross-Validation
SeyedAmirReza Hamidi - Kamal Mohamed-Pour - Mohammad Yousefi
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 43.6.0
