语音识别理论、论文和PPT

02-06 12:00

#0

语音识别理论、论文和PPT
对于近研一期间所学进行总结，包括理论部分和实践部分，之间主要包括本人认为比较好的论文，以及也有自己的看法
ppt主要包括本人研一期间使用kaldi语音识别工具构建GMM-HMM、NN-HMM语音识别声学模型
论文主要包括一些研一到到现在所看的论文，之后还会不定期更新论文，如果对理论比较感兴趣的同行可以持续关注
INTERSPEECH Google'PPT
其中包含谷歌开源的18年INTERSPEECH的PPT，个人觉得写得非常棒，系统

A COMPARABLE STUDY OF MODELING UNITS FOR END-TO-END.pdf

A Survey of the Recent Architectures of Deep Convolutional Neural Networks.pdf

ABCNN Attention-Based Convolutional Neural Network.pdf

An Overview of End2End for ASR.pdf

Convolutional Attention-based Seq2Seq Neural Network for End-to-End ASR.pdf

Hybrid CTCAttention Architecture for End-to-End Speech Recognition.pdf

Interspeech 2018_ Tutorial E2E Speech Recognition.pdf

PPT10个子项

2018.03.16.pptx

2018.03.30.pptx

2018.04.13.pptx

2018.04.28.pptx

2018.05.19.pptx

2018.06.02.pptx

2018.06.23.pptx

2018.07.08.pptx

2018.07.21.pptx

Transformer5个子项

A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition.pdf

SPEECH-TRANSFORMER A NO-RECURRENCE SEQUENCE-TO-SEQUENCE MODEL.pdf

Syllable-Based Sequence-to-Sequence Speech Recognition with the.pdf

The Illustrated Transformer – Jay Alammar – Visualizing machine learning one concept at a time.pdf

htk3个子项

HTK手册_第一章.pdf

HTK手册_第三章.pdf

HTK手册_第二章.pdf

icassp186个子项

GRADIENT-BASED ACTIVE LEARNING QUERY STRATEGY.pdf

JOINT ENDPOINTING AND DECODING WITH END-TO-END MODELS.pdf

M-VECTORS SUB-BAND BASED ENERGY MODULATION FEATURES FOR.pdf

MULTIMODAL GROUNDING FOR SEQUENCE-TO-SEQUENCE SPEECH RECOGNITION.pdf

Modulation Filter Learning Using Deep Variational.pdf

SUBWORD REGULARIZATION AND BEAM SEARCH DECODING.pdf

kaldi10个子项

Kaldi 学习-02.pdf

Kaldi 学习03.pdf

Kaldi 学习基础篇（二）--Shell 学习基础.pdf

Kaldi 语音识别基础教程-01.pdf

asr_lecture_1.pdf

asr_lecture_2.pdf

asr_lecture_3.pdf

chain model 翻译 - 简书.pdf

kaldi的全部资料_v0.6.pdf

中文论文57个子项

Chinese Micro-Blog Sentiment Analysis Based on Multi-Channels Convolutional Neural Networks.pdf

一种基于CLMF的深度卷积神经网络模型_随婷婷.pdf

一种基于全卷积神经网络的横担姿态测量方法_吴巍_郭飞_郭毓_郭健.pdf

一种改进的DNN_HMM的语音识别方法_李云红.pdf

一种融合全局时空特征的CNNs动作识别方法_王珂.pdf

分离多路卷积神经网络研究_宋超.pdf

图像理解中的卷积神经网络_常亮.pdf

基于BLSTM_CTC和WFST的端到端中文语音识别系统_姚煜.pdf

基于CNN和BiLSTM网络特征融合的文本情感分析_李洋.pdf

基于CTC准则的普通话识别及改进_张立民.pdf

基于全卷积神经网络的焊缝特征提取的研究_张永帅.pdf

基于全卷积神经网络的空间植物图像快速识别_樊帅.pdf

基于卷积神经网络的连续语音识别_张晴晴.pdf

基于双向长短时记忆_联结时序分类_省略_态转换器的端到端中文语音识别系统_姚煜.pdf

基于双网络级联卷积神经网络的设计_潘兵.pdf

基于多尺度残差网络的压缩感知重构算法_练秋生.pdf

基于改进VGG卷积神经网络的棉花病害识别模型_张建华.pdf

基于改进卷积神经网络的快速车辆检测_朱锋彬.pdf

基于改进卷积神经网络算法的语音识别_杨洋.pdf

基于改进的卷积神经网络的人群密度估计_贾翻连.pdf

基于改进的卷积神经网络脑电信号情感识别_田莉莉.pdf

基于深层神经网络的语音识别声学建模研究.pdf

基于深度SE_DenseNet的航班延误预测模型_吴仁彪.pdf

基于迁移学习的噪声鲁棒语音识别声学建模_易江燕.pdf

基于链接时序分类的日语语音识别_孙健_郭武.pdf

多路卷积神经网络的轮胎缺陷图像分类_崔雪红.pdf

多通道卷积神经网络图像识别方法_易超人.pdf

改进深度残差卷积神经网络的LDCT图像估计_高净植.pdf

融合多维度卷积神经网络的肺结节分类方法_吴保荣.pdf

跨语言声学模型在维吾尔语语音识别中的应用_努尔麦麦提_尤鲁瓦斯.pdf

零基础入门深度学习(1) - 感知器 - 作业部落 Cmd Markdown 编辑阅读器.pdf

零基础入门深度学习(2) - 线性单元和梯度下降 - 作业部落 Cmd Markdown 编辑阅读器.pdf

零基础入门深度学习(3) - 神经网络和反向传播算法 - 作业部落 Cmd Markdown 编辑阅读器.pdf

零基础入门深度学习(4) - 卷积神经网络 - 作业部落 Cmd Markdown 编辑阅读器.pdf

零基础入门深度学习(5) - 循环神经网络 - 作业部落 Cmd Markdown 编辑阅读器.pdf

零基础入门深度学习(6) - 长短时记忆网络(LSTM) - 作业部落 Cmd Markdown 编辑阅读器.pdf

零基础入门深度学习(7) - 递归神经网络 - 作业部落 Cmd Markdown 编辑阅读器.pdf

硕士论文2个子项

英文论文52个子项

Attention Is All You Need.pdf

2017_End-to-end speech recognition and keyword search on low-resource languages.pdf

AN EMPIRICAL EXPLORATION OF CTC ACOUSTIC MODELS (2).pdf

APPLYING CONVOLUTIONAL NEURAL NETWORKS CONCEPTS TO HYBRID NN-HMM MODEL FOR SPEECH RECOGNITION.pdf

Adaptive Very Deep Convolutional Residual Network for Noise Robust Speech Recognition.pdf

An Empirical Exploration of Recurrent Network Architectures.pdf

Analysis of CNN-based Speech Recognition System using Raw Speech as Input.pdf

Applying Connectionist Temporal Classification Objective Function to Chinese Mandarin Speech Recognition (2).pdf

Articulatory Feature Extraction using CTC to build Articulatory Classifiers Without Forced Frame Alignments for Speech Recognition.pdf

Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift.pdf

Connectionist Temporal Classification Labelling Unsegmented.pdf

Convolutional Neural Networks at Constrained Time Cost.pdf

Convolutional Neural Networks for Speech Recognition.pdf

DEEP CONVOLUTIONAL NEURAL NETWORKS FOR LVCSR.pdf

DENSENET FOR DENSE FLOW (1).pdf

Deep Residual Learning for Image Recognition.pdf

Deep Speech 2 End-to-End Speech Recognition in English and Mandarin.pdf

Deep Speech_ Scaling up end-to-end speech recognition.pdf

Densely Connected Convolutional Networks.pdf

Dropout_ A Simple Way to Prevent Neural Networks from Overfitting.pdf

EESEN END-TO-END SPEECH RECOGNITION USING DEEP RNN MODELS AND WFST-BASED DECODING.pdf

END-TO-END ATTENTION-BASED LARGE VOCABULARY SPEECH RECOGNITION.pdf

END-TO-END SPEECH RECOGNITION AND KEYWORD SEARCH ON LOW-RESOURCE LANGUAGES.pdf

Fault State Recognition of Rolling Bearing Based Fully Convolutional Network.pdf

Feedforward Sequential Memory Neural Networks.pdf

First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs.pdf

Going Deeper with Convolution.pdf

HYBRID SPEECH RECOGNITION WITH DEEP BIDIRECTIONAL LSTM.pdf

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning.pdf

LEARNING ACOUSTIC FRAME LABELING FOR SPEECH RECOGNITION WITH RECURRENT NEURAL NETWORKS.pdf

LONG SHORT-TERM MEMORY BASED RECURRENT NEURAL NETWORK ARCHITECTURES FOR LARGE VOCABULARY SPEECH RECOGNITION.pdf

Long Short_Term _省略_ Training Corpus_Don.pdf

MobileNetV2_ Inverted Residuals and Linear Bottlenecks.pdf

MobileNets_ Efficient Convolutional Neural Networks for Mobile Vision.pdf

Multi-Path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained “Hard Faces”.pdf

Multimodal 2D+3D Facial Expression Recognition With Deep Fusion Convolutional Neural Network.pdf

Recent Advances in Convolutional Neural Networks.pdf

Research on Optimization Method of Convolutional Nerual Network.pdf

Rethinking the Inception Architecture for Computer Vision.pdf

SPEECH RECOGNITION WITH DEEP RECURRENT NEURAL NETWORKS.pdf

Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks.pdf

THCHS-30_A_Free_Chinese_Speech_Corpus.pdf

The Kaldi Speech Recognition Toolkit.pdf

Towards End-to-End Speech Recognition for Chinese Mandarin Using Long Short-Term Memory Recurrent Neural Networks.pdf

Towards End-to-End Speech Recognition with Recurrent Neural Networks.pdf

Two-Stage Deep Learning for Noisy-Reverberant Speech Enhancement.pdf

VERY DEEP CONVOLUTIONAL NEURAL NETWORKS FOR ROBUST SPEECH RECOGNITION.pdf

Very Deep Convolutional Neural Networks for LVCSR.pdf

deep learning_Methods and Applications.pdf

基于TDNN_FSMN的蒙古语语音识别技术研究_王勇和.pdf

深浅层特征及模型融合的说话人识别_仲伟峰.pdf

语音识别中的深度协同学习方法.pdf

鉴别性训练2个子项

最大互信息用于语音识别_张春涛.pdf

鉴别性最大后验概率线性回归说话人自适应研究_齐耀辉.pdf

点赞回复