این سایت در حال حاضر پشتیبانی نمی شود و امکان دارد داده های نشریات بروز نباشند
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