Natural Language Processing for Speech and Text: From Beginner to Advanced

Focused View

Wuraola Oyewusi

2:00:04

0 View

01 - Introduction

01 - Fundamentals of natural language processing.mp4

00:58

02 - NLP course strategy.mp4

01:05

02 - 1. Introduction to Natural Language Processing (NLP)

01 - What is natural language processing (NLP).mp4

02:20

02 - What are sequences.mp4

02:58

03 - Applications of natural language processing in text data.mp4

03:52

04 - Applications of natural language processing in speech data.mp4

02:23

05 - Historical evolution of NLP tasks and techniques.mp4

04:16

06 - How computers understand sequences in NLP.mp4

00:57

03 - 2. Natural Language Processing for Text Techniques

01 - Text preprocessing.mp4

03:06

02 - Text preprocessing using NLTK.mp4

07:10

03 - Text representation.mp4

02:18

04 - Text representation One-hot encoding.mp4

02:06

05 - One-hot encoding using scikit-learn.mp4

03:32

06 - Text representation N-grams.mp4

02:21

07 - N-grams representation using NLTK.mp4

03:03

08 - Text representation Bag-of-words (BoW).mp4

02:01

09 - Bag-of-words representation using scikit-learn.mp4

02:29

10 - Text representation Term frequency-inverse document frequency (TF-IDF).mp4

01:50

11 - TF-IDF representation using scikit-learn.mp4

02:08

12 - Text representation Word embeddings.mp4

02:56

13 - Word2vec embedding using Gensim.mp4

09:08

14 - Embedding with pretrained spaCy model.mp4

05:07

15 - Sentence embedding using the Sentence Transformers library.mp4

03:42

16 - Text representation Pre-trained language models (PLMs).mp4

02:34

17 - Pre-trained language models using Transformers.mp4

05:43

04 - 3. Natural Language Processing for Speech Techniques

01 - Speech representation Mel-frequency cepstral coefficients.mp4

02:10

02 - Mel-frequency cepstral coefficients (MFCCs) using librosa.mp4

03:28

03 - Speech representation Linear predictive cepstral coefficients (LPCCs).mp4

01:51

04 - Linear predictive coding (LPC) using librosa.mp4

03:58

05 - Speech representation Gammatone filterbank features.mp4

01:21

06 - Gammatone filterbank features using librosa.mp4

03:16

07 - Speech representation Spectrograms.mp4

02:25

08 - Spectrograms using fast Fourier transform (FFT) in librosa.mp4

03:24

09 - Speech representation Speech embeddings.mp4

01:53

10 - Speech embeddings using wav2vec in Transformers.mp4

05:13

05 - 4. Applied Natural Language Processing Algorithms and Tasks

01 - Algorithms for natural language processing tasks.mp4

02:05

02 - Types of algorithms in natural language processing.mp4

02:50

03 - Rule-based Regular expressions.mp4

01:51

04 - Regular expression tasks using the re library.mp4

02:42

05 - Rule-based Rule-based parsing.mp4

01:34

Description

With the recent surge in large language models, it's particularly relevant to explore the evolution of NLP techniques, from traditional methods to current industry standards. In this course, Wuraola Oyewusi—an experienced data scientist and machine learning and artificial intelligence professional—helps you build a strong foundation in natural language processing (NLP) concepts and addresses the end-to-end application of NLP. Learn about both text and speech data while you explore the theoretical background of NLP concepts, the historical evolution of NLP techniques, and current applications of NLP representation techniques for both text and speech data. Dive into code-based practice exercises for preprocessing techniques and tasks for both text and speech data. Plus, check out a wide range of Python libraries, including NLTK, spaCy, Hugging Face, Transformers, librosa, scikit-learn, gensim, and torchaudio.

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Natural Language Processing

Wuraola Oyewusi

Instructor's Courses

Experienced data scientist (DS), machine learning (ML), and artificial intelligence (AI) professional with expertise in natural language processing (NLP), healthcare, data curation, and research. Recognized as a UK Global Talent in AI, Machine Learning, and Data Science

Linkedin Learning

View courses Linkedin Learning

LinkedIn Learning is an American online learning provider. It provides video courses taught by industry experts in software, creative, and business skills. It is a subsidiary of LinkedIn. All the courses on LinkedIn fall into four categories: Business, Creative, Technology and Certifications. It was founded in 1995 by Lynda Weinman as Lynda.com before being acquired by LinkedIn in 2015. Microsoft acquired LinkedIn in December 2016.