Readings

There are more listed readings this week. This is partly because we’ve listed 3 separate sections of a chapter from Jurafsky and Martin, but also so that there are some extra resources for you to draw on as we start assignment 1. There are also some recommended readings from Paul Taylor’s classic textbook on Text-To-Speech with a more extensive discussion. The level of detail in Taylor’s textbook is beyond what is required for this course (we use it for the second semester Speech Synthesis course). But if you are interested in reading more details on the processes touched upon in the Jurafsky and Martin Chapter 8, Taylor’s book is the place to look. Chapters 4 and 5 are also relevant to text processing/the TTS front-end.

The recommended paper by Fitt and Isard maybe handy for understanding the pronunciation lexicon used in the TTS assignment.

Reading

Jurafsky & Martin (2nd ed) – Section 8.1 – Text Normalisation

We need to normalise the input text so that it contains a sequence of pronounceable words.

Jurafsky & Martin (2nd ed) – Section 8.2 – Phonetic Analysis

Each word in the normalised text needs a pronunciation. Most words will be found in the dictionary, but for the remainder we must predict pronunciation from spelling.

Jurafsky & Martin (2nd ed) – Section 8.3 – Prosodic Analysis

Beyond getting the phones right, we also need to consider other aspects of speech such as intonation and pausing.

Plag (2003) – Word formation in English: Chapter 1 Basic Concepts

An introductory text of word structure/morphology in English. Useful to read if you come from a non-linguistic background.