Dutch CV dictionary v2.0.0#
@misc{Ahn_Chodroff_2022,
author={Ahn, Emily and Chodroff, Eleanor},
title={VoxCommunis Corpus},
address={\url{https://osf.io/t957v}},
publisher={OSF},
year={2022},
month={Jan}
}
Acoustic models |
Installation#
Install from the MFA command line:
mfa model download dictionary dutch_cv
Or download from the release page.
Intended use#
This dictionary is intended for forced alignment of Dutch transcripts.
This dictionary uses the Epitran phone set for Dutch, and was used in training the Dutch Epitran acoustic model. Pronunciations can be added on top of the dictionary, as long as no additional phones are introduced.
Performance Factors#
When trying to get better alignment accuracy, adding pronunciations is generally helpful, especially for different styles and dialects. The most impactful improvements will generally be seen when adding reduced variants that involve deleting segments/syllables common in spontaneous speech. Alignment must include all phones specified in the pronunciation of a word, and each phone has a minimum duration (by default 10ms). If a speaker pronounces a multisyllabic word with just a single syllable, it can be hard for MFA to fit all the segments in, so it will lead to alignment errors on adjacent words as well.
Ethical considerations#
Deploying any Speech-to-Text model into any production setting has ethical implications. You should consider these implications before use.
Demographic Bias#
You should assume every machine learning model has demographic bias unless proven otherwise. For pronunciation dictionaries, it is often the case that transcription accuracy and lexicon coverage for the prestige variety modeled in this dictionary compared to other variants. If you are using this dictionary in production, you should acknowledge this as a potential issue.
IPA Charts#
Consonants#
Obstruent symbols to the left of are unvoiced and those to the right are voiced.
Manner |
Labial |
Labiodental |
Alveolar |
Alveopalatal |
Palatal |
Velar |
Glottal |
---|---|---|---|---|---|---|---|
Nasal |
Occurrences: 7,728 Examples: * maps?: [m ɑ p s] * amber: [ɑ m b ɛ r] * moet,: [m uː t] * matig: [m aː t ɪ x] |
Occurrences: 27,213 Examples: * ons.: [ɔ n s] * slang: [s l ɑ n x] * vanop: [v aː n ɔ p] * horen: [h oː r ɛ n] |
Occurrences: 2,218 Examples: * ing.: [ɪ ŋ] * enge: [ɛ ŋ eː] * lang.: [l ɑ ŋ] * lang?: [l ɑ ŋ] |
||||
Stop |
Occurrences: 7,965 Examples: * maps?: [m ɑ p s] * pff,: [p f f] * speld: [s p ɛ l t] * plaat: [p l aː t] Occurrences: 5,207 Examples: * amber: [ɑ m b ɛ r] * birma: [b ɪ r m aː] * boot.: [b oː t] * boek.: [b uː k] |
Occurrences: 25,922 Examples: * vlot.: [v l ɔ t] * moet,: [m uː t] * flits: [f l ɪ t s] * fiets: [f iː t s] Occurrences: 10,541 Examples: * goud.: [ɣ ɑ w d] * goed.: [ɣ uː d] * dicht: [d ɪ x t] * de...: [d ɛ] |
Occurrences: 2,775 Examples: * scala: [s c aː l aː] * cool.: [c oː l] * cuba: [c yː b aː] * exact: [ɛ k s ɑ c t] |
Occurrences: 8,693 Examples: * rekje: [r ɛ k j eː] * krim: [k r ɪ m] * klap: [k l ɑ p] * kei-: [k ɛ j] |
|||
Sibilant |
Occurrences: 18,602 Examples: * ons.: [ɔ n s] * slang: [s l ɑ n x] * maps?: [m ɑ p s] * scala: [s c aː l aː] Occurrences: 2,648 Examples: * inzet: [ɪ n z ɛ t] * zijn?: [z ɛ j n] * zelf:: [z ɛ l f] * zei:: [z ɛ j] |
Occurrences: 169 Examples: * ijsje: [ɛ j ʃ eː] * show: [ʃ ɔ ʋ] * lesje: [l ɛ ʃ eː] * sushi: [s ʏ ʃ iː] |
|||||
Fricative |
Occurrences: 3,253 Examples: * flits: [f l ɪ t s] * pff,: [p f f] * fiets: [f iː t s] * treft: [t r ɛ f t] Occurrences: 7,695 Examples: * vlot.: [v l ɔ t] * ivo: [iː v oː] * vanop: [v aː n ɔ p] * lijve: [l ɛ j v eː] |
Occurrences: 2,824 Examples: * hals: [h ɑ l s] * horen: [h oː r ɛ n] * hoog: [h oː x] * hoop;: [h oː p] |
|||||
Approximant |
Occurrences: 1,204 Examples: * goud.: [ɣ ɑ w d] * duwde: [d y w d eː] * eeuw.: [eː w] * fauna: [f a w ʏ n aː] |
Occurrences: 3,679 Examples: * weg,: [ʋ ɛ ɣ] * wél: [ʋ ɛ l] * kwam.: [k ʋ ɑ m] * dwang: [t ʋ ɑ n x] |
Occurrences: 7,576 Examples: * gijs: [ɣ ɛ j s] * rekje: [r ɛ k j eː] * jij: [j ɛ j] * kei-: [k ɛ j] Occurrences: 1,513 Examples: * duidt: [d œ ɥ t t] * vuil: [v œ ɥ l] * luik.: [l œ ɥ k] * luid: [l œ ɥ t] |
||||
Trill |
Occurrences: 25,183 Examples: * amber: [ɑ m b ɛ r] * serie: [s eː r iː eː] * birma: [b ɪ r m aː] * rekje: [r ɛ k j eː] |
||||||
Lateral |
Occurrences: 12,771 Examples: * vlot.: [v l ɔ t] * slang: [s l ɑ n x] * scala: [s c aː l aː] * las: [l ɑ s] |
Vowels#
Vowel symbols to the left of are unrounded and those to the right are rounded.
Front |
Near-Front |
Central |
Near-Back |
Back |
|
---|---|---|---|---|---|
Close |
Occurrences: 33 Examples: * nieuw: [n i w] Occurrences: 7,769 Examples: * fiets: [f iː t s] * ivo: [iː v oː] * serie: [s eː r iː eː] * rijen: [r iː j ɛ n] Occurrences: 150 Examples: * duwde: [d y w d eː] * ruw: [r y w] * ruw.: [r y w] * rauwe: [r a w y w eː] Occurrences: 1,440 Examples: * vuur.: [v yː r] * uber?: [yː b ɛ r] * cuba: [c yː b aː] * unie,: [yː n iː] |
Occurrences: 152 Examples: * bloei: [p l u j iː] * doei!: [d u j] * groei: [x r u j iː] * knoei: [k n u j iː] Occurrences: 2,009 Examples: * moet,: [m uː t] * toe!: [t uː] * goed.: [ɣ uː d] * droeg: [t r uː x] |
|||
Occurrences: 11,446 Examples: * flits: [f l ɪ t s] * matig: [m aː t ɪ x] * birma: [b ɪ r m aː] * krim: [k r ɪ m] Occurrences: 3,184 Examples: * euro,: [øː ʏ r ɔ] * ruk: [r ʏ k] * lukt.: [l ʏ k t] * forum: [f oː r ʏ m] |
|||||
Close-Mid |
Occurrences: 17,824 Examples: * serie: [s eː r iː eː] * rekje: [r ɛ k j eː] * leeg: [l eː x] * lenen: [l eː n ɛ n] Occurrences: 553 Examples: * euro,: [øː ʏ r ɔ] * geur: [ɣ øː r] * deur: [d øː r] * keus: [k øː s] |
Occurrences: 7 Examples: * dürüm: [d ʏ̈ r ʏ̈ m] |
Occurrences: 6,564 Examples: * ivo: [iː v oː] * horen: [h oː r ɛ n] * moge: [m oː ɣ eː] * hoog: [h oː x] |
||
Open-Mid |
Occurrences: 36,397 Examples: * amber: [ɑ m b ɛ r] * gijs: [ɣ ɛ j s] * weg,: [ʋ ɛ ɣ] * speld: [s p ɛ l t] Occurrences: 1,513 Examples: * duidt: [d œ ɥ t t] * vuil: [v œ ɥ l] * luik.: [l œ ɥ k] * luid: [l œ ɥ t] |
Occurrences: 54 Examples: * zeeën: [z eː ɛ̈ n] |
Occurrences: 2 Examples: |
Occurrences: 7,345 Examples: * vlot.: [v l ɔ t] * ons.: [ɔ n s] * vanop: [v aː n ɔ p] * euro,: [øː ʏ r ɔ] |
|
Open |
Occurrences: 311 Examples: * fauna: [f a w ʏ n aː] * nauw.: [n a w] * paul: [p a w l] * paus.: [p a w s] Occurrences: 9,140 Examples: * scala: [s c aː l aː] * matig: [m aː t ɪ x] * birma: [b ɪ r m aː] * plaat: [p l aː t] |
Occurrences: 9,262 Examples: * slang: [s l ɑ n x] * maps?: [m ɑ p s] * las: [l ɑ s] * amber: [ɑ m b ɛ r] |