Inducing concatenative units from machine readable dictionaries and corpora for speech synthesis

on the set of diphones is quite straightforward in the sense that it suuces to take the phoneme inventory of a language , and simply combine each phoneme with every other one. For example, taking the approximately 35 French phonemes, 1225 phonemic pairs (35x35) constitute the complete and exhaustive starting diphone inventory. On the other hand, deciding on the set of triphones, quadriphones and larger units raises diicult questions about the nature of phonemes in a given language such as: (1) stability vs instability in a coarticulatory environment, (2) size of overall inventory, and (3) frequency of that unit in the language, in combination with factors (1) and (2). We report on experiments with four diierent databases, with comparisons between the resources regarding their n-gram frequency output. The rst two databases consist of pronunciation eld information from two dictionaries, the Encyclopedic Robert French dictionary 16] with 85,000 headwords, and the smaller Collins Gem 13] containing 15,000 words. For comparison, we use two text corpora, the Hansard (about 2.5 million words) and the smaller Tubach and Boe 31] corpus (80,000 words); both corpora were processed by a set of grapheme-to-phoneme rules 18]. A frequency extraction program was applied to all four resources to extract trigram phonemic frequencies; this serves as a basis for comparison between dictionary derived data and corpus derived frequencies.