FPGA Implementation for GMM-Based Speaker Identification
Author:
Affiliation:
1. School of Electronic, Electrical and Computer Engineering, University of Birmingham, Edgbaston, Birmingham B15 2TT, UK
2. School of Computer and Communication Engineering, University Malaysia Perlis, 01000 Kangar, Perlis, Malaysia
Abstract
Publisher
Hindawi Limited
Subject
Hardware and Architecture
Link
http://downloads.hindawi.com/journals/ijrc/2011/420369.pdf
Reference7 articles.
1. Robust text-independent speaker identification using Gaussian mixture speaker models
2. Scalable architecture for word HMM-based speech recognition and VLSI implementation in complete system
3. Generalized mel frequency cepstral coefficients for large-vocabulary speaker-independent continuous-speech recognition
4. An Efficient Digital VLSI Implementation of Gaussian Mixture Models-Based Classifier
Cited by 19 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. GMM-Based Speaker Verification System with Hardware MFCC in SoC Design;Multimedia Tools and Applications;2023-12-14
2. Approximate Toom–Cook FFT with sparsity aware error tuning in a shared memory architecture;Integration;2023-03
3. B2N2: Resource efficient Bayesian neural network accelerator using Bernoulli sampler on FPGA;Integration;2023-03
4. FPGA Design for Efficient Speech Processing System;2022 2nd Asian Conference on Innovation in Technology (ASIANCON);2022-08-26
5. Always-On Speech Recognition Terminals: Designs based on approximate computing methods;IEEE Nanotechnology Magazine;2022-02
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3