GithubHelp home page GithubHelp logo

gaoyiyeah / asr_syllable Goto Github PK

View Code? Open in Web Editor NEW

This project forked from zw76859420/asr_syllable

0.0 2.0 0.0 6.13 MB

基于卷积神经网络的语音识别声学模型的研究

License: GNU General Public License v3.0

Python 100.00%

asr_syllable's Introduction

ASR_Syllable

首先感谢西安电子科技大学聂师兄,北理工詹师兄,工大薛师兄,以及携程郝师兄等好友对本项目提出高贵建议;
采用端到端方法构建声学模型,以音节为建模单元,采用DCNN-CTC网络结构,希望集众人力量改进以音节为建模单元的声学模型。

配置环境要求

python 3.x
keras 2.0
Tensorflow 1.8.0
numpy
wave
python_speech_features
random
os
scipy
difflib

THCHS-30数据

程序的实验数据可以从Thchs30下载,在此感谢清华大学对语音识别领域的贡献; 下载完成解压后放在程序的同级目录; 程序不仅是对中文语音识别声学模型以字为建模单元的的构建,而且为英文语音识别以字为建模单元提供一定的指导意义。

算法框架

拼帧与跳帧

代码位置在 ./general_function/pinzhen.py

CTC损失函数:

采用DCNN-CTC构建语音识别声学模型;
CTC损失函数介绍可以观看本人的博客;
(1)CTC原理介绍;
(2)CTC损失函数推导;

网络构建;

(1)构建类似VGG网络架构,Conv-BN-Conv-BN-Maxpool-Dropout
(2)采用MNIST数据集构建Densenet网络架构,自己可以直接把Densenet网络架构用于声学模型,脚本对应的是speechmodel_17;
(3)为了解决CTC在最后Dense层分类无法捕捉前后信息,我对Dense层加入了Attention机制,代码如下: ####融入了attention机制于全连接层;
dense1 = Dense(units=512, activation='relu', use_bias=True, kernel_initializer='he_normal')(reshape)
attention_prob = Dense(units=512, activation='softmax', name='attention_vec')(dense1)
attention_mul = multiply([dense1, attention_prob])
dense1 = BatchNormalization(epsilon=0.0002)(attention_mul)
dense1 = Dropout(0.3)(dense1)

实验结果

DCNN-CTC:25.09%
Densenet-CTC:SER=31.23%,优化之前为SER=32.27%
DCNN-Attention-CTC:SER=24.32%

实验改进

欢迎各位同行对本声学模型提供宝贵建议;
个人博客 包含自己近期的学习总结

asr_syllable's People

Contributors

zw76859420 avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.