""" definition of the phones to be used. """ ## phones in IPA. phoneset_ipa = [ # vowels 'i̯', 'i̯ⁿ', 'y', 'i', 'i.', 'iⁿ', 'i:', 'i:ⁿ', 'ɪ', 'ɪⁿ', 'ɪ.', #'ɪ:', # not included in lex.ipa 'ɪ:ⁿ', 'e', 'e:', 'e:ⁿ', 'ə', 'əⁿ', 'ə:', 'ɛ', 'ɛ.', 'ɛⁿ', 'ɛ:', 'ɛ:ⁿ', 'a', 'aⁿ', 'a.', 'a:', 'a:ⁿ', 'ṷ', 'ṷ.', 'ṷⁿ', #'ú', # only appears in word 'feeste'(út) and 'gaste'(út) which are 'f e: s t ə' and 'yn' in lex_asr. 'u', 'uⁿ', 'u.', 'u:', 'u:ⁿ', 'ü', 'ü.', 'üⁿ', 'ü:', 'ü:ⁿ', 'o', 'oⁿ', 'o.', 'o:', 'o:ⁿ', 'ö', 'ö.', 'öⁿ', 'ö:', 'ö:ⁿ', 'ɔ', 'ɔ.', 'ɔⁿ', 'ɔ:', 'ɔ:ⁿ', #'ɔ̈', # not included in lex.ipa 'ɔ̈.', 'ɔ̈:', # plosives 'p', 'b', 't', 'tⁿ', 'd', 'k', 'g', 'ɡ', # = 'g' # nasals 'm', 'n', 'ŋ', # fricatives 'f', 'v', 's', 's:', 'z', 'zⁿ', 'x', 'h', # tap and flip 'r', 'r.', # only appears in word 'mearpartijestelsel'(does not exist in lex_asr) and 'tenoarpartij'. 'r:', # only appears in word 'mûsearflearmûs' and 'sjochdêr'. # approximant 'j', 'j.', 'l' ] ## the list of multi character phones. # for example, the length of 'i̯ⁿ' is 3, but in the codes it is treated as one letter. multi_character_phones_ipa = [i for i in phoneset_ipa if len(i) > 1] multi_character_phones_ipa.sort(key=len, reverse=True)