Tailoring Pronunciations with LexiconKit

A lexicon is a collection of word pronunciations that a speech recognition engine (i.e., recognizer) uses to improve recognition accuracy and a speech synthesis engine (i.e., synthesizer) uses to enhance its word pronunciation.

Chant LexiconKit handles the complexities of managing and persisting word pronunciations. This allows your application to enhance the quality of speech recognition and speech synthesis and offer administrative features for maintaining word pronunciations.

Recognizers and synthesizers have unique formats for word pronunciations, lexicon formats, and approaches for runtime inclusion. LexiconKit supports the following recognizer and synthesizers and their lexicons formats.

Speech API	Alphabets	File Format
Acapela TTS	ipa, acatts	.dic
Cepstral Swift API	swift	.txt
Microsoft (SAPI5, Speech Platform, WindowsMedia)	ipa, sapi, ups	W3C .pls
Microsoft Azure	ipa, sapi, ups, x-sampa	(W3C) .pls

For more information about tailoring pronunciations with LexiconKit, review the following topics:

• Lexicon Editing and
• Lexicon Management Applications.