کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
1123002 | 1488527 | 2012 | 8 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Robust speech recognition by extracting invariant features
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
موضوعات مرتبط
علوم انسانی و اجتماعی
علوم انسانی و هنر
هنر و علوم انسانی (عمومی)
پیش نمایش صفحه اول مقاله
چکیده انگلیسی
A long-term goal of machine learning is providing techniques to overcome the unwanted variations and noise to improve the recognition accuracy. In this study we used a model based on deep architectures to provide better representations of Input. In order to increase the capacity of recurrent Neural Network, we present a model to share common features across data. Also by using this method the extracted components will be invariant to speaker variations. We compared the performance of this method with our previous research. The results show that the proposed model is more useful in removing noise and unwanted variability.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Procedia - Social and Behavioral Sciences - Volume 32, 2012, Pages 230-237
Journal: Procedia - Social and Behavioral Sciences - Volume 32, 2012, Pages 230-237