|
|
International Journal of Information and Communication Technology Research (IJICT، جلد ۱۵، شماره ۳، صفحات ۵۳-۶۵
|
|
|
| عنوان فارسی |
|
|
| چکیده فارسی مقاله |
|
|
| کلیدواژه‌های فارسی مقاله |
|
|
| عنوان انگلیسی |
NMF-based Improvement of DNN and LSTM Pre-Training for Speech Enhancemet |
|
| چکیده انگلیسی مقاله |
A novel pre-training method is proposed to improve deep-neural-networks (DNN) and long-short-term-memory (LSTM) performance, and reduce the local minimum problem for speech enhancement. We propose initializing the last layer weights of DNN and LSTM by Non-Negative-Matrix-Factorization (NMF) basis transposed values instead of random weights. Due to its ability to extract speech features even in presence of non-stationary noises, NMF is faster and more successful than previous pre-training methods for network convergence. Using NMF basis matrix in the first layer along with another pre-training method is also proposed. To achieve better results, we further propose training individual models for each noise type based on a noise classification strategy. The evaluation of the proposed method on TIMIT data shows that it outperforms the baselines significantly in terms of perceptual-evaluation-of-speech-quality (PESQ) and other objective measures. Our method outperforms the baselines in terms of PESQ up to 0.17, with an improvement percentage of 3.4%. |
|
| کلیدواژه‌های انگلیسی مقاله |
pre-training, deep neural networks (DNN), long short-term memory (LSTM), non-negative matrix factorization (NMF), speech enhancement, basis matrix, noise classification |
|
| نویسندگان مقاله |
| Razieh Safari Dehnavi
Department of Electrical Engineering Amirkabir University of Technology (Tehran Polytechnic) Tehran, Iran
| Sanaz Seyedin
Department of Electrical Engineering Amirkabir University of Technology (Tehran Polytechnic) Tehran, Iran
|
|
| نشانی اینترنتی |
http://ijict.itrc.ac.ir/browse.php?a_code=A-10-670-1&slc_lang=en&sid=1 |
| فایل مقاله |
فایلی برای مقاله ذخیره نشده است |
| کد مقاله (doi) |
|
| زبان مقاله منتشر شده |
en |
| موضوعات مقاله منتشر شده |
فناوری ارتباطات |
| نوع مقاله منتشر شده |
پژوهشی |
|
|
|
برگشت به:
صفحه اول پایگاه |
نسخه مرتبط |
نشریه مرتبط |
فهرست نشریات
|