Computational Linguistics - IPA and XSampa
Discover an essential requirement for linguist when applying to Apple, Amazon or Appen
What you will learn
Discover X-Sampa, the phonetic alphabet asked for by Apple
Learn the computer version of the International Phonetic Alphabet (IPA)
Level up your CV mastering phonetics
Be able to create your own converter in Python
Why take this course?
Welcome to Computational Linguistics - IPA and XSampa
In this course, the very first course on X-Sampa you will discover the phonetic alphabet that computers understand, and the top-tier companies ask for.
In Computational Linguistics - IPA and XSampa, you will learn the International Phonetic Alphabet, known as IPA, and X-Sampa. X-Sampa has turned crucial for linguist positions at top-tier companies such as Amazon, Apple, and Appen, among others. X-Sampa is the phonetic alphabet that computers understand. You will use it to tell a virtual assistant how to pronounce, and you will use it for STT, to transform recordings into text so that machines can understand.
The course has two parts:
Part I: You will learn the International Phonetic Alphabet (IPA) applied to English. If you are not a native English speaker, there is nothing to worry about, since you will be able to easily apply the knowledge to any language. You will learn the phonemes that construct every sound in any language and how they are represented in IPA. You will go through the types and features of consonants. Finally, we will see how these IPA representations are transformed into X-Sampa.
Part II: We will use the knowledge from Part I to create our own converter in Python. By the end of this part, you will be able to introduce a word or sentence in IPA and your code will give you back the X-Sampa version for it, and vice versa.
Each part has its own file. Part I has a PDF attached to Lecture 7 in Section 2. You will find all the theoretical documentation needed for the course. It covers explanations for IPA and X-Sampa. The second document will be a resource in Lecture 32 in Section 7. It is a Jupyter notebook (extension .ipynb) with the full Python code for the converter. Nevertheless, I strongly recommend not to download it and create your own code while watching the videos in Section 7. You can download Anaconda or transform the .ipynb file into a .py file and modify it in PyCharm or your favourite code editor.
Previous requirements are just two: look for any word in any language in any dictionary and realize that there is something like /ˌriːkənˈstrʌkʃən/ next to that word, and know a little about Python (dictionaries and functions are more than enough). This is not essential, since the Python code is explained in detail in the videos.
Our full journey will cover:
Introduction to the course
International Phonetic Alphabet overview
Features of consonants
Types of consonants
Vowels
From IPA to X-Sampa
Final project: create your own converter in Python