Ctrl+K
Ctrl+K

Maltese CV dictionary v2.0.0#

  • Maintainer: Vox Communis

  • Language: Maltese

  • Dialect: N/A

  • Phone set: Epitran

  • Number of words: 12,252

  • Phones: b c d d͡ʒ f h i j k l m n p r s t t͡s t͡ʃ v w y z ħ ħː ɐ ɔ ɛ ɡ ɪ ʃ ʃː ʊ ʔ ˤː

  • License: CC-0

  • Compatible MFA version: v2.0.0

  • Citation:

@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}
}

Installation#

Install from the MFA command line:

mfa model download dictionary maltese_cv

Or download from the release page.

Intended use#

This dictionary is intended for forced alignment of Maltese transcripts.

This dictionary uses the Epitran phone set for Maltese, and was used in training the Maltese 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

Pharyngeal

Glottal

Nasal
Occurrences:
3,471
Examples:
* ħadem:
[ħ ɐ d ɛ m]
* james:
[j ɐ m ɛ s]
* prima:
[p r ɪ m ɐ]
* mitt:
[m ɪ t t]
Occurrences:
5,720
Examples:
* fondi:
[f ɔ n d ɪ]
* ngħix:
[n ˤː ɪ ʃ]
* eno:
[ɛ n ɔ]
* open:
[ɔ p ɛ n]

Stop
Occurrences:
2,006
Examples:
* prima:
[p r ɪ m ɐ]
* port.:
[p ɔ r t]
* open:
[ɔ p ɛ n]
* patri:
[p ɐ t r ɪ]
Occurrences:
1,904
Examples:
* club:
[c l ʊ b]
* ikteb:
[ɪ k t ɛ b]
* beto:
[b ɛ t ɔ]
* ebda:
[ɛ b d ɐ]
Occurrences:
7,513
Examples:
* ikteb:
[ɪ k t ɛ b]
* mitt:
[m ɪ t t]
* beto:
[b ɛ t ɔ]
* età:
[ɛ t ɐ]
Occurrences:
2,633
Examples:
* ħadem:
[ħ ɐ d ɛ m]
* roads:
[r ɔ ɐ d s]
* mod.:
[m ɔ d]
* fondi:
[f ɔ n d ɪ]
Occurrences:
364
Examples:
* club:
[c l ʊ b]
* care:
[c ɐ r ɛ]
* clint:
[c l ɪ n t]
* luca:
[l ʊ c ɐ]
Occurrences:
2,403
Examples:
* ikteb:
[ɪ k t ɛ b]
* każi,:
[k ɐ z ɪ]
* kasu:
[k ɐ s ʊ]
* nikbu:
[n ɪ k b ʊ]
Occurrences:
678
Examples:
* agius:
[ɐ ɡ ɪ ʊ s]
* gost.:
[ɡ ɔ s t]
* night:
[n ɪ ɡ t]
* gwida:
[ɡ w ɪ d ɐ]
Occurrences:
902
Examples:
* oħloq:
[ɔ ħ l ɔ ʔ]
* x'qal:
[ʃ ʔ ɐ l]
* qabeż:
[ʔ ɐ b ɛ z]
* fuqu.:
[f ʊ ʔ ʊ]

Affricate
Occurrences:
1,284
Examples:
* franz:
[f r ɐ n t͡s]
* mizzi:
[m ɪ t͡s t͡s ɪ]
* prezz:
[p r ɛ t͡s t͡s]
* foloz:
[f ɔ l ɔ t͡s]
Occurrences:
668
Examples:
* ċerti:
[t͡ʃ ɛ r t ɪ]
* ċerta:
[t͡ʃ ɛ r t ɐ]
* ċara.:
[t͡ʃ ɐ r ɐ]
* paċi:
[p ɐ t͡ʃ ɪ]
Occurrences:
882
Examples:
* x'ġie:
[ʃ d͡ʒ i ɛ]
* ħriġt:
[ħ r ɪ d͡ʒ t]
* aġent:
[ɐ d͡ʒ ɛ n t]
* liġi:
[l ɪ d͡ʒ ɪ]

Sibilant
Occurrences:
4,083
Examples:
* agius:
[ɐ ɡ ɪ ʊ s]
* sħiħ.:
[s ħ ɪ ħ]
* james:
[j ɐ m ɛ s]
* roads:
[r ɔ ɐ d s]
Occurrences:
831
Examples:
* żero.:
[z ɛ r ɔ]
* każi,:
[k ɐ z ɪ]
* qabeż:
[ʔ ɐ b ɛ z]
* tuża:
[t ʊ z ɐ]
Occurrences:
832
Examples:
* x'qal:
[ʃ ʔ ɐ l]
* xiex?:
[ʃ i ɛ ʃ]
* mixli:
[m ɪ ʃ l ɪ]
* ngħix:
[n ˤː ɪ ʃ]
Occurrences:
86
Examples:
* taxxa:
[t ɐ ʃː ɐ]

Fricative
Occurrences:
1,792
Examples:
* f'air:
[f ɐ ɪ r]
* fondi:
[f ɔ n d ɪ]
* fuqu.:
[f ʊ ʔ ʊ]
* nafu:
[n ɐ f ʊ]
Occurrences:
693
Examples:
* vera:
[v ɛ r ɐ]
* prova:
[p r ɔ v ɐ]
* vera?:
[v ɛ r ɐ]
* vot.:
[v ɔ t]
Occurrences:
1,124
Examples:
* ħadem:
[ħ ɐ d ɛ m]
* sħiħ.:
[s ħ ɪ ħ]
* oħloq:
[ɔ ħ l ɔ ʔ]
* ħriġt:
[ħ r ɪ d͡ʒ t]
Occurrences:
17
Examples:
* dmugħ:
[d m ʊ ħː]
* qligħ:
[ʔ l ɪ ħː]
* bejgħ:
[b ɛ j ħː]
* ibigħ:
[ɪ b ɪ ħː]
Occurrences:
70
Examples:
* leah:
[l ɛ ɐ h]
* youth:
[y ɔ ʊ t h]
* narah:
[n ɐ r ɐ h]
* worth:
[w ɔ r t h]

Approximant
Occurrences:
1,082
Examples:
* sew!:
[s ɛ w]
* wlied:
[w l i ɛ d]
* town:
[t ɔ w n]
* qawwa:
[ʔ ɐ w w ɐ]
Occurrences:
3,245
Examples:
* james:
[j ɐ m ɛ s]
* juru:
[j ʊ r ʊ]
* xejn.:
[ʃ ɛ j n]
* jiġix:
[j ɪ d͡ʒ ɪ ʃ]

Trill
Occurrences:
5,181
Examples:
* f'air:
[f ɐ ɪ r]
* żero.:
[z ɛ r ɔ]
* prima:
[p r ɪ m ɐ]
* roads:
[r ɔ ɐ d s]

Lateral
Occurrences:
6,771
Examples:
* club:
[c l ʊ b]
* oħloq:
[ɔ ħ l ɔ ʔ]
* x'qal:
[ʃ ʔ ɐ l]
* mixli:
[m ɪ ʃ l ɪ]

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:
981
Examples:
* xiex?:
[ʃ i ɛ ʃ]
* x'ġie:
[ʃ d͡ʒ i ɛ]
* wlied:
[w l i ɛ d]
* żieda:
[z i ɛ d ɐ]
Occurrences:
94
Examples:
* tommy:
[t ɔ m m y]
* ray:
[r ɐ y]
* copy:
[c ɔ p y]
* fifty:
[f ɪ f t y]
Occurrences:
10,789
Examples:
* agius:
[ɐ ɡ ɪ ʊ s]
* f'air:
[f ɐ ɪ r]
* sħiħ.:
[s ħ ɪ ħ]
* prima:
[p r ɪ m ɐ]
Occurrences:
3,155
Examples:
* agius:
[ɐ ɡ ɪ ʊ s]
* club:
[c l ʊ b]
* hu!:
[ʊ]
* ommu.:
[ɔ m m ʊ]

Close-Mid

Open-Mid
Occurrences:
6,228
Examples:
* ħadem:
[ħ ɐ d ɛ m]
* żero.:
[z ɛ r ɔ]
* james:
[j ɐ m ɛ s]
* ikteb:
[ɪ k t ɛ b]
Occurrences:
3,654
Examples:
* oħloq:
[ɔ ħ l ɔ ʔ]
* żero.:
[z ɛ r ɔ]
* roads:
[r ɔ ɐ d s]
* mod.:
[m ɔ d]
Occurrences:
10,905
Examples:
* agius:
[ɐ ɡ ɪ ʊ s]
* f'air:
[f ɐ ɪ r]
* ħadem:
[ħ ɐ d ɛ m]
* x'qal:
[ʃ ʔ ɐ l]

Open

Other phones#

  • ˤː

On this page
Show Source