book

Deep Learning Approach for Natural Language Processing, Speech, and Computer Vision

Name: Deep Learning Approach for Natural Language Processing, Speech, and Computer Vision
ISBN: 9781000875607

by L. Ashok Kumar, D. Karthika Renuka

May 2023

Intermediate to advanced

246 pages

6h 21m

English

CRC Press

Read now

Unlock full access

Cover
Half Title
Title
Copyright
Dedication
Contents
About the Authors
Preface
Acknowledgments
Chapter 1 Introduction
Learning Outcomes1.1 Introduction1.1.1 Subsets of Artificial Intelligence1.1.2 Three Horizons of Deep Learning Applications1.1.3 Natural Language Processing1.1.4 Speech Recognition1.1.5 Computer Vision1.2 Machine Learning Methods for NLP, Computer Vision (CV), and Speech1.2.1 Support Vector Machine (SVM)1.2.2 Bagging1.2.3 Gradient-boosted Decision Trees (GBDTs)1.2.4 Naïve Bayes1.2.5 Logistic Regression1.2.6 Dimensionality Reduction Techniques1.3 Tools, Libraries, Datasets, and Resources for the Practitioners1.3.1 TensorFlow1.3.2 Keras1.3.3 Deeplearning4j1.3.4 Caffe1.3.5 ONNX1.3.6 PyTorch1.3.7 scikit-learn1.3.8 NumPy1.3.9 Pandas1.3.10 NLTK1.3.11 Gensim1.3.12 Datasets1.4 SummaryBibliography

Chapter 2 Natural Language Processing
Learning Outcomes2.1 Natural Language Processing2.2 Generic NLP Pipeline2.2.1 Data Acquisition2.2.2 Text Cleaning2.3 Text Pre-processing2.3.1 Noise Removal2.3.2 Stemming2.3.3 Tokenization2.3.4 Lemmatization2.3.5 Stop Word Removal2.3.6 Parts of Speech Tagging2.4 Feature Engineering2.5 Modeling2.5.1 Start with Simple Heuristics2.5.2 Building Your Model2.5.3 Metrics to Build Model2.6 Evaluation2.7 Deployment2.8 Monitoring and Model Updating2.9 Vector Representation for NLP2.9.1 One Hot Vector Encoding2.9.2 Word Embeddings2.9.3 Bag of Words2.9.4 TF-IDF2.9.5 N-gram2.9.6 Word2Vec2.9.7 Glove2.9.8 ElMo2.10 Language Modeling with n-grams2.10.1 Evaluating Language Models2.10.2 Smoothing2.10.3 Kneser-Ney Smoothing2.11 Vector Semantics and Embeddings2.11.1 Lexical Semantics2.11.2 Vector Semantics2.11.3 Cosine for Measuring Similarity2.11.4 Bias and Embeddings2.12 SummaryBibliography
Chapter 3 State-of-the-Art Natural Language Processing
Learning Outcomes3.1 Introduction3.2 Sequence-to-Sequence Models3.2.1 Sequence3.2.2 Sequence Labeling3.2.3 Sequence Modeling3.3 Recurrent Neural Networks3.3.1 Unrolling RNN3.3.2 RNN-based POS Tagging Use Case3.3.3 Challenges in RNN3.4 Attention Mechanisms3.4.1 Self-attention Mechanism3.4.2 Multi-head Attention Mechanism3.4.3 Bahdanau Attention3.4.4 Luong Attention3.4.5 Global Attention versus Local Attention3.4.6 Hierarchical Attention3.5 Transformer Model3.5.1 Bidirectional Encoder, Representations, and Transformers (BERT)3.5.2 GPT33.6 SummaryBibliography
Chapter 4 Applications of Natural Language Processing
Learning Outcomes4.1 Introduction4.2 Word Sense Disambiguation4.2.1 Word Senses4.2.2 WordNet: A Database of Lexical Relations4.2.3 Approaches to Word Sense Disambiguation4.2.4 Applications of Word Sense Disambiguation4.3 Text Classification4.3.1 Building the Text Classification Model4.3.2 Applications of Text Classification4.3.3 Other Applications4.4 Sentiment Analysis4.4.1 Types of Sentiment Analysis4.5 Spam Email Classification4.5.1 History of Spam4.5.2 Spamming Techniques4.5.3 Types of Spams4.6 Question Answering4.6.1 Components of Question Answering System4.6.2 Information Retrieval-based Factoid Question and Answering4.6.3 Entity Linking4.6.4 Knowledge-based Question Answering4.7 Chatbots and Dialog Systems4.7.1 Properties of Human Conversation4.7.2 Chatbots4.7.3 The Dialog-state Architecture4.8 SummaryBibliography
Chapter 5 Fundamentals of Speech Recognition
Learning Outcomes5.1 Introduction5.2 Structure of Speech5.3 Basic Audio Features5.3.1 Pitch5.3.2 Timbral Features5.3.3 Rhythmic Features5.3.4 MPEG-7 Features5.4 Characteristics of Speech Recognition System5.4.1 Pronunciations5.4.2 Vocabulary5.4.3 Grammars5.4.4 Speaker Dependence5.5 The Working of a Speech Recognition System5.5.1 Input Speech5.5.2 Audio Pre-processing5.5.3 Feature Extraction5.6 Audio Feature Extraction Techniques5.6.1 Spectrogram5.6.2 MFCC5.6.3 Short-Time Fourier Transform5.6.4 Linear Prediction Coefficients (LPCC)5.6.5 Discrete Wavelet Transform (DWT)5.6.6 Perceptual Linear Prediction (PLP)5.7 Statistical Speech Recognition5.7.1 Acoustic Model5.7.2 Pronunciation Model5.7.3 Language Model5.7.4 Conventional ASR Approaches5.8 Speech Recognition Applications5.8.1 In Banking5.8.2 In-Car Systems5.8.3 Health Care5.8.4 Experiments by Different Speech Groups for Large-Vocabulary Speech Recognition5.8.5 Measure of Performance5.9 Challenges in Speech Recognition5.9.1 Vocabulary Size5.9.2 Speaker-Dependent or -Independent5.9.3 Isolated, Discontinuous, and Continuous Speech5.9.4 Phonetics5.9.5 Adverse Conditions5.10 Open-source Toolkits for Speech Recognition5.10.1 Frameworks5.10.2 Additional Tools and Libraries5.11 SummaryBibliography
Chapter 6 Deep Learning Models for Speech Recognition
Learning Outcomes6.1 Traditional Methods of Speech Recognition6.1.1 Hidden Markov Models (HMMs)6.1.2 Gaussian Mixture Models (GMMs)6.1.3 Artificial Neural Network (ANN)6.1.4 HMM and ANN Acoustic Modeling6.1.5 Deep Belief Neural Network (DBNN) for Acoustic Modelling6.2 RNN-based Encoder–Decoder Architecture6.3 Encoder6.4 Decoder6.5 Attention-based Encoder–Decoder Architecture6.6 Challenges in Traditional ASR and the Motivation for End-to-End ASR6.7 SummaryBibliography
Chapter 7 End-to-End Speech Recognition Models
Learning Outcomes7.1 End-to-End Speech Recognition Models7.1.1 Definition of End-to-End ASR System7.1.2 Connectionist Temporal Classification (CTC)7.1.3 Deep Speech7.1.4 Deep Speech 27.1.5 Listen, Attend, Spell (LAS) Model7.1.6 JASPER7.1.7 QuartzNet7.2 Self-supervised Models for Automatic Speech Recognition7.2.1 Wav2Vec7.2.2 Data2Vec7.2.3 HuBERT7.3 Online/Streaming ASR7.3.1 RNN-transducer-Based Streaming ASR7.3.2 Wav2Letter for Streaming ASR7.3.3 Conformer Model7.4 SummaryBibliography
Chapter 8 Computer Vision Basics
Learning Outcomes8.1 Introduction8.1.1 Fundamental Steps for Computer Vision8.1.2 Fundamental Steps in Digital Image Processing8.2 Image Segmentation8.2.1 Steps in Image Segmentation8.3 Feature Extraction8.4 Image Classification8.4.1 Image Classification Using Convolutional Neural Network (CNN)8.4.2 Convolution Layer8.4.3 Pooling or Down Sampling Layer8.4.4 Flattening Layer8.4.5 Fully Connected Layer8.4.6 Activation Function8.5 Tools and Libraries for Computer Vision8.5.1 OpenCV8.5.2 MATLAB8.6 Applications of Computer Vision8.6.1 Object Detection8.6.2 Face Recognition8.6.3 Number Plate Identification8.6.4 Image-based Search8.6.5 Medical Imaging8.7 SummaryBibliography
Chapter 9 Deep Learning Models for Computer Vision
Learning Outcomes9.1 Deep Learning for Computer Vision9.2 Pre-trained Architectures for Computer Vision9.2.1 LeNet9.2.2 AlexNet9.2.3 VGG9.2.4 Inception9.2.5 R-CNN9.2.6 Fast R-CNN9.2.7 Faster R-CNN9.2.8 Mask R-CNN9.2.9 YOLO9.3 SummaryBibliography
Chapter 10 Applications of Computer Vision
Learning Outcomes10.1 Introduction10.2 Optical Character Recognition10.2.1 Code Snippets10.2.2 Result Analysis10.3 Face and Facial Expression Recognition10.3.1 Face Recognition10.3.2 Facial Recognition System10.3.3 Major Challenges in Recognizing Face Expression10.3.4 Result Analysis10.4 Visual-based Gesture Recognition10.4.1 Framework Used10.4.2 Code Snippets10.4.3 Result Analysis10.4.4 Major Challenges in Gesture Recognition10.5 Posture Detection and Correction10.5.1 Framework Used10.5.2 Squats10.5.3 Result Analysis10.6 SummaryBibliography
Index

Overview

Deep Learning Approach for Natural Language Processing, Speech, and Computer Vision provides an overview of general deep learning methodology and its applications of natural language processing (NLP), speech and computer vision tasks.

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Deep Learning for Natural Language Processing

Publisher Resources

ISBN: 9781000875607

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills