请选择 进入手机版 | 继续访问电脑版

Hello Mat

 找回密码
 立即注册
查看: 8234|回复: 2

语音识别学习网站

  [复制链接]

1064

主题

1239

帖子

13

金钱

管理员

Rank: 9Rank: 9Rank: 9

积分
21393
发表于 2016-9-17 11:34:59 | 显示全部楼层 |阅读模式
语音识别
VOICEBOX
Department of Electrical and Electronic Engineering | Imperial College London
CLEAR - Centre for Law-Enforcement Audio Research
Speech Filing System
Internet Institute for Speech and Hearing
Speech Recognition - CodeProjectVoice-activated OS; Author: Tambi Ashmoz; Updated: 27 Feb 2004; Section: Audio and Video; Chapter: Multimedia; Updated: 27 Feb 2004Speech recognition - Wikipedia, the free encyclopedia
Dynamic Time Warping (DTW) — mlpy v3.5.0 documentation
Search | Electrical & Computer Engineering Department
Redefining Our Relationship with Information - Bell LabsBell Laboratories (also known as Bell Labs and formerly known as AT&T Bell Laboratories and Bell Telephone Laboratories) is the research and development subsidiary of Alcatel-Lucent. Bell Laboratories operates its headquarters in Murray Hill, New Jersey, United States, and has research and development facilities throughout the world.
EECS E6870 Speech Recognition
Kaldi: Kaldi
Speech Recognition Grammar Specification Version 1.0
CSE 6328 Speech and Language Processing (Fall 2012) [CSE6328]
Automatic Speech Recognition(ASR) 学习资源
HTK Speech Recognition ToolkitHTK - Hidden Markov Model Toolkit - Speech Recognition toolkit
Speech recognition - ArchWiki
ASR webpage
Speech Synthesis & Speech Recognition
The Bing Speech Recognition Control
Can I use... Support tables for HTML5, CSS3, etc
FreeSpeech Realtime Speech Recognition and DictationLive conversion of spoken words into text. An open-source alternative to Dragon Naturally Speaking�.
Deep Neural Networks for Acoustic Modeling in Speech Recognition - Microsoft Research
EURASIP ASMP | Full text | Noisy training for deep neural networks in speech recognitionDeep neural networks (DNNs) have gained remarkable success in speech recognition, partially attributed to the flexibility of DNN models in learning complex patterns of speech signals. This flexibility, however, may lead to serious over-fitting and hence miserable performance degradation in adverse acoustic conditions such as those with high ambient noises. We propose a noisy training approach to tackle this problem: by injecting moderate noises into the training data intentionally and randomly, more generalizable DNN models can be learned. This ‘noise injection’ technique, although known to the neural computation community already, has not been studied with DNNs which involve a highly complex objective function. The experiments presented in this paper confirm that the noisy training approach works well for the DNN model and can provide substantial performance improvement for DNN-based speech recognition.
Acceleration Strategies for Speech Recognition Based on Deep Neural NetworksMechatronics Engineering, Computing and Information Technology: Acceleration Strategies for Speech Recognition Based on Deep Neural Networks
Deep Neural Networks for Acoustic Modeling in Speech Recognition | deepak gopinath - Academia.eduBy deepak gopinath in Machine Learning and Data Mining.
Deep Neural Networks Power Big Gains in Speech RecognitionTen years ago, Bill Gates declared speech recognition as one of the "holy grails" of computing challenges that would fall within the next decade. Right on
Deep Neural Networks for Acoustic Modeling in Speech Recognition - HKUST Institutional RepositoryDeep Neural Networks for Acoustic Modeling in Speech Recognition
Deep Neural Networks for Acoustic... preview & related info | Mendeley(2012) Hinton et al. Signal Processing Magazine, IEEE. Read by researchers in: 30% Computer and Information Science, 5% Engineering. Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each...
Deep-Neural-Network Speech Recognition Debuts - Inside Microsoft Research - Site Home - TechNet BlogsLearn how computing research projects and computer-science technologies developed by Microsoft are integrated with products and used in other ways that benefit society..
Kaldi: Deep Neural Networks in Kaldi
Hidden Markov Model (HMM) Toolbox for Matlab
Demonstration of speech dereverberation/denoising on Keisuke Kinoshita's Website (木下慶介)
NML RevCon-RR - Softwares - Products | TACSYSTEM&nbsp; Features - Novel dereberb...</MTIfNonEmpty>
算法QQ  3283892722
群智能算法链接http://halcom.cn/forum.php?mod=forumdisplay&fid=73
回复

使用道具 举报

1064

主题

1239

帖子

13

金钱

管理员

Rank: 9Rank: 9Rank: 9

积分
21393
 楼主| 发表于 2016-9-17 11:45:21 | 显示全部楼层

机器学习论坛【招募版主】

机器学习论坛【招募版主】
算法QQ  3283892722
群智能算法链接http://halcom.cn/forum.php?mod=forumdisplay&fid=73

0

主题

5

帖子

6

金钱

禁止发言

积分
26
发表于 2020-9-26 17:25:09 | 显示全部楼层
提示: 作者被禁止或删除 内容自动屏蔽
回复 支持 反对

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

Python|Opencv|MATLAB|Halcom.cn

GMT+8, 2022-7-3 14:24 , Processed in 0.180561 second(s), 21 queries .

Powered by Discuz! X3.4

Copyright © 2001-2021, Tencent Cloud.

快速回复 返回顶部 返回列表