ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Robust continuous digit recognition using Reservoir Computing

Jalalvand, Azarakhsh*; Triefenbach, Fabian; Demuynck, Kris; Martens, Jean-Pierre
COMPUTER SPEECH AND LANGUAGE2015-3DOI: 10.1016/j.csl.2014.09.006
16被引1阅读
引用收藏
分享

摘要

It is acknowledged that Hidden Markov Models (HMMs) with Gaussian Mixture Models (GMMs) as the observation density functions achieve excellent digit recognition performance at high signal to noise ratios (SNRs). Moreover, many years of research have led to good techniques to reduce the impact of noise, distortion and mismatch between training and test conditions on the recognition accuracy. Nevertheless, we still await systems that are truly robust against these confounding factors. The present paper extends recent work on acoustic modeling based on Reservoir Computing (RC), a concept that has its roots in Machine Learning. By introducing a novel analysis of reservoirs as non-linear dynamical systems, new insights are gained and translated into a new reservoir design recipe that is extremely simple and highly comprehensible in terms of the dynamics of the acoustic features and the modeled acoustic units. By tuning the reservoir to these dynamics, one can create RC-based systems that not only compete well with conventional systems in clean conditions, but also degrade more gracefully in noisy conditions. Control experiments show that noise robustness follows from the random fixation of the reservoir neurons whereas, tuning the reservoir dynamics increases the accuracy without compromising the noise-robustness.

学科与关键词

关键词
Reservoir ComputingRecurrent Neural NetworksAcoustic modelingAutomatic Speech RecognitionNoise robust spoken digit recognition
相关
加载中…
  • On the application of reservoir computing networks for noisy image recognition
    Jalalvand, Azarakhsh*; Demuynck, Kris; De Neve, Wesley; Martens, Jean-PierreNEUROCOMPUTING, 2018, 277: 237-248.被引 49
  • Recent advances in physical reservoir computing: A review
    Tanaka, Gouhei*; Yamane, Toshiyuki; Heroux, Jean Benoit; Nakane, Ryosho; Kanazawa, Naoki; Takeda, Seiji; Numata, Hidetoshi; Nakano, Daiju; Hirose, AkiraNeural Networks, 2019, 115: 100-123.被引 1102
  • Determining Reservoir Topologies from Short-Term Memory in Echo State Networks
    Qianli, Ma; Weibiao, ChenCommunications in Computer and Information Science, Springer Berlin Heidelberg, 64-71, 2012.
查看全部 →

发表信息

论文状态
公开发表
期刊
COMPUTER SPEECH AND LANGUAGE
发表日期
2015-03
卷期
第 30 卷, 第 1 期
页码
135-158
DOI
10.1016/j.csl.2014.09.006
语言
ENGLISH
期刊收录
SCIE
期刊等级
Q2
成果收录
SCIE
资助标注
European Community's Seventh Framework Program (FP7) [231267]; Flemish Science Foundation (FWO) [G.0088.09N]

作者

  • J

    Jalalvand, Azarakhsh (通讯) (第一作者)

  • T

    Triefenbach, Fabian

查看全部 4 位作者收起作者
  • D

    Demuynck, Kris

  • M

    Martens, Jean-Pierre

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417