Image to Image Translation based on Convolutional Neural Network Approach for Speech Declipping
Publish Year: 1398
نوع سند: مقاله کنفرانسی
زبان: English
View: 511
This Paper With 5 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
این Paper در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ETECH04_066
تاریخ نمایه سازی: 27 بهمن 1398
Abstract:
Clipping, as a current nonlinear distortion, often occurs due to the limited dynamic range of audio recorders. It degrades the speech quality and intelligibility and adverselyaffects the performances of speech and speaker recognitions. In this paper, we focus on enhancement of clipped speech by using a fully convolutional neural network as U-Net. Motivated by the idea of image-to-image translation, we propose a declipping approach, namely U-Net declipper in which the magnitude spectrum images of clipped signals are translated to the corresponding images of clean ones. The experimental results show that the proposed approach outperforms other declipping methods in terms of both quality and intelligibility measures, especially in severe clipping cases. Moreover, the superior performance of the U-Net declipper over the well-known declipping methods is verified in additive Gaussian noise conditions.
Keywords:
Authors
Hamidreza Baradaran Kashani
Electrical Engineering Faculty Amirkabir University of Technology Tehran, Iran
Ata Jodeiri
School of Electrical & Computer Engineering University of Tehran Tehran, Iran
Mohammad Mohsen Goodarzi
Department of Biomedical Engineering, Buein Zahra Technical University, Buein Zahra, Qazvin, Iran
Shabnam Gholamdokht Firooz
School of Electrical & Computer Engineering University of Tehran Tehran, Iran