کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
403875 677365 2015 9 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Low-dimensional recurrent neural network-based Kalman filter for speech enhancement
ترجمه فارسی عنوان
فیلتر کولمن مبتنی بر شبکه عصبی کمینه برای تقویت گفتار
کلمات کلیدی
شبکه عصبی مکرر، تقویت گفتار، سر و صدای غیرقانونی، برآورد محدودیت سر و صدا
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
چکیده انگلیسی

This paper proposes a new recurrent neural network-based Kalman filter for speech enhancement, based on a noise-constrained least squares estimate. The parameters of speech signal modeled as autoregressive process are first estimated by using the proposed recurrent neural network and the speech signal is then recovered from Kalman filtering. The proposed recurrent neural network is globally asymptomatically stable to the noise-constrained estimate. Because the noise-constrained estimate has a robust performance against non-Gaussian noise, the proposed recurrent neural network-based speech enhancement algorithm can minimize the estimation error of Kalman filter parameters in non-Gaussian noise. Furthermore, having a low-dimensional model feature, the proposed neural network-based speech enhancement algorithm has a much faster speed than two existing recurrent neural networks-based speech enhancement algorithms. Simulation results show that the proposed recurrent neural network-based speech enhancement algorithm can produce a good performance with fast computation and noise reduction.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neural Networks - Volume 67, July 2015, Pages 131–139
نویسندگان
, ,