# Pronunciation Lexicon **Domain:** Computational Linguistics / Speech Technology / Lexicography **Doc Type:** Canonical Resource-Architecture Node **Maturity:** Developed **Related:** [[wiki/Phonological Representation|Phonological Representation]], [[wiki/CMU Pronouncing Dictionary|CMU Pronouncing Dictionary]], [[wiki/Prosody and Syllabification|Prosody and Syllabification]], [[wiki/Approximate Phonological Matching|Approximate Phonological Matching]] --- ## Definition **A Pronunciation Lexicon maps written lexical forms to one or more structured pronunciations.** Entries commonly encode phonemes and stress, allowing software to operate on sound rather than infer it unreliably from spelling. Pronunciation multiplicity is essential. Heteronyms share an orthographic form while differing in sound and meaning. Treating one spelling as one pronunciation collapses distinct rhyme classes, syllable patterns and lexical senses. ## Symbolic Language Engine Context The [[wiki/Symbolic Language Engine|Symbolic Language Engine]] carried pronunciation multiplicity through the full system. The interface displayed separate tabs for the two pronunciations of _dove_, each producing its own rhyme set. The lexicon also supported interactive syllable counting and phrase-level phonological indexing. Unknown words create a production problem. A system needs a defensible fallback—rules, user correction or a neural pronunciation model—while marking inferred pronunciations differently from lexicon-attested ones. ## Key Insight **A pronunciation is an evidence-bearing lexical object, not a decorative annotation on spelling.** ## See Also [[wiki/CMU Pronouncing Dictionary|CMU Pronouncing Dictionary]], [[wiki/Phonological Representation|Phonological Representation]], [[wiki/Approximate Phonological Matching|Approximate Phonological Matching]], [[wiki/Prosody and Syllabification|Prosody and Syllabification]], [[wiki/Provenance-Sensitive Multiplicity|Provenance-Sensitive Multiplicity]] ## Sources / Provenance - Primary project account: [[projects/Ten Years Building a Symbolic Language Engine|Ten Years Building a Symbolic Language Engine]]. - [[wiki/CMU Pronouncing Dictionary|CMU Pronouncing Dictionary]] and project-specific pronunciation resources.