Evan Kirshenbaum’s feature set used in his ASCII transcription of the International Phonetic Alphabet (IPA)[1], [2] describes the phonemes in a way consistent with how the phonemes are organised in the IPA code chart. That is the approach used in the Phonemes document to describe the phonemes in a phoneme definition file.
Those phoneme features often represent the action of more than one articulatory mechanism used to produce speech, or affect the same area. Internally, espeak-ng makes use of the articulatory model, not the IPA descriptions. This document describes how the feature-based IPA model is mapped to the articulatory model.
People working on adding new voices or languages do not need to read this document, but should instead read the Phonemes document. This is intended for people working on the espeak-ng codebase, or people interested in how espeak-ng works internally.
NOTE: This model is in the process of being implemented. As such, the current implementation does not reflect this document.
Kirshenbaum, Evan, Representing IPA phonetics in ASCII (HTML). 1993.
Kirshenbaum, Evan, Representing IPA phonetics in ASCII (PDF). 2001.
International Phonetic Association, The International Phonetic Alphabet and the IPA Chart. 2015. Creative Commons Attribution-Sharealike 3.0 Unported License (CC-BY-SA).
Wikipedia. International Phonetic Alphabet. 2017. Creative Commons Attribution-Sharealike 3.0 Unported License (CC-BY-SA).
Wikipedia. Extensions to the International Phonetic Alphabet. 2017, Creative Commons Attribution-Sharealike 3.0 Unported License (CC-BY-SA).