English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  Items with full text/Total items : 94986/125531 (76%)
Visitors : 31080228      Online Users : 433
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    政大機構典藏 > 理學院 > 資訊科學系 > 期刊論文 >  Item 140.119/121475
    Please use this identifier to cite or link to this item: http://nccur.lib.nccu.edu.tw/handle/140.119/121475

    Title: Experimental Study on Extreme Learning Machine Applications for Speech Enhancement
    Authors: Hussain, Tassadaq;Siniscalchi, Sabato Marco;Lees, Chi-Chun;Wang, Syu-Siang;Tsao, Yu;Liao, Wen-Hung
    Liao, Wen-Hung
    Contributors: 資科系
    Keywords: Speech enhancement;artificial neural networks;extreme learning machine;hierarchical extreme learning machines
    Date: 2017
    Issue Date: 2018-12-22 11:56:37 (UTC+8)
    Abstract: In wireless telephony and audio data mining applications, it is desirable that noise suppression can be made robust against changing noise conditions and operates in real time (or faster). The learning effectiveness and speed of artificial neural networks are therefore critical factors in applications for speech enhancement tasks. To address these issues, we present an extreme learning machine (ELM) framework, aimed at the effective and fast removal of background noise from a single-channel speech signal, based on a set of randomly chosen hidden units and analytically determined output weights. Because feature learning with shallow ELM may not be effective for natural signals, such as speech, even with a large number of hidden nodes, hierarchical ELM (H-ELM) architectures are deployed by leveraging sparse auto-encoders. In this manner, we not only keep all the advantages of deep models in approximating complicated functions and maintaining strong regression capabilities, but we also overcome the cumbersome and time-consuming features of both greedy layer-wise pre-training and back-propagation (BP)-based fine tuning schemes, which are typically adopted for training deep neural architectures. The proposed ELM framework was evaluated on the Aurora-4 speech database. The Aurora-4 task provides relatively limited training data, and test speech data corrupted with both additive noise and convolutive distortions for matched and mismatched channels and signal-to-noise ratio (SNR) conditions. In addition, the task includes a subset of testing data involving noise types and SNR levels that are not seen in the training data. The experimental results indicate that when the amount of training data is limited, both ELM- and H-ELM-based speech enhancement techniques consistently outperform the conventional BP-based shallow and deep learning algorithms, in terms of standardized objective evaluations, under various testing conditions.
    Relation: IEEE Access , Volume 5 , Page 25542 - 25554
    Data Type: article
    DOI 連結: http://dx.doi.org/10.1109/ACCESS.2017.2766675
    DOI: 10.1109/ACCESS.2017.2766675
    Appears in Collections:[資訊科學系] 期刊論文

    Files in This Item:

    File Description SizeFormat

    All items in 政大典藏 are protected by copyright, with all rights reserved.

    社群 sharing

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback