Ctrl+K
Ctrl+K

Uzbek CV dictionary v2.0.0#

  • Maintainer: Vox Communis

  • Language: Uzbek

  • Dialect: N/A

  • Phone set: Epitran

  • Number of words: 910

  • Phones: a b d̪ d͡ʒ e h i j k l m n o p q r s t̪ t͡s t͡ʃ u v z ŋ ɒ ɡ ɸ ʁ ʃ ʔ χ

  • 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}
}

Acoustic models

Installation#

Install from the MFA command line:

mfa model download dictionary uzbek_cv

Or download from the release page.

Intended use#

This dictionary is intended for forced alignment of Uzbek transcripts.

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

Dental

Alveolar

Alveopalatal

Palatal

Velar

Uvular

Glottal

Nasal
Occurrences:
214
Examples:
* so'm:
[s o m]
* mavzu:
[m a v z u]
* ham:
[h a m]
* qaram:
[q a r a m]
Occurrences:
344
Examples:
* oltin:
[ɒ l t̪ i n]
* o'n:
[o n]
* necha:
[n e t͡ʃ a]
* uyni:
[u j n i]
Occurrences:
50
Examples:
* bunga:
[b u ŋ a]
* uning:
[u n i ŋ]
* o'ng:
[o ŋ]
* teng:
[t̪ e ŋ]

Stop
Occurrences:
35
Examples:
* sopol:
[s ɒ p ɒ l]
* parvo:
[p a r v ɒ]
* gap:
[ɡ a p]
* gapi:
[ɡ a p i]
Occurrences:
201
Examples:
* qolib:
[q ɒ l i b]
* buni:
[b u n i]
* bois:
[b ɒ i s]
* kutib:
[k u t̪ i b]
Occurrences:
315
Examples:
* oltin:
[ɒ l t̪ i n]
* tog':
[t̪ ɒ ʁ]
* olti:
[ɒ l t̪ i]
* taxta:
[t̪ a χ t̪ a]
Occurrences:
269
Examples:
* dod:
[d̪ ɒ d̪]
* aldov:
[a l d̪ ɒ v]
* dedi:
[d̪ e d̪ i]
* juda:
[d͡ʒ u d̪ a]
Occurrences:
179
Examples:
* nikoh:
[n i k ɒ h]
* kutib:
[k u t̪ i b]
* yuk:
[j u k]
* tark:
[t̪ a r k]
Occurrences:
156
Examples:
* ishga:
[i ʃ ɡ a]
* sigir:
[s i ɡ i r]
* agar:
[a ɡ a r]
* go'yo:
[ɡ o j ɒ]
Occurrences:
176
Examples:
* qolib:
[q ɒ l i b]
* qaram:
[q a r a m]
* qayta:
[q a j t̪ a]
* ovqat:
[ɒ v q a t̪]
Occurrences:
11
Examples:
* ya'ni:
[j a ʔ n i]

Affricate
Occurrences:
4
Examples:
Occurrences:
55
Examples:
* hech:
[h e t͡ʃ]
* necha:
[n e t͡ʃ a]
* uchun:
[u t͡ʃ u n]
* o'ch:
[o t͡ʃ]
Occurrences:
25
Examples:
* juvon:
[d͡ʒ u v ɒ n]
* juda:
[d͡ʒ u d̪ a]
* javob:
[d͡ʒ a v ɒ b]
* jihat:
[d͡ʒ i h a t̪]

Sibilant
Occurrences:
178
Examples:
* so'm:
[s o m]
* sof:
[s ɒ ɸ]
* safar:
[s a ɸ a r]
* sol.:
[s ɒ l]
Occurrences:
84
Examples:
* mavzu:
[m a v z u]
* tez:
[t̪ e z]
* hozir:
[h ɒ z i r]
* yozma:
[j ɒ z m a]
Occurrences:
147
Examples:
* ishga:
[i ʃ ɡ a]
* shaxs:
[ʃ a χ s]
* shu:
[ʃ u]
* besh:
[b e ʃ]

Fricative
Occurrences:
36
Examples:
* sof:
[s ɒ ɸ]
* safar:
[s a ɸ a r]
* fikr:
[ɸ i k r]
* foyda:
[ɸ ɒ j d̪ a]
Occurrences:
60
Examples:
* mavzu:
[m a v z u]
* aldov:
[a l d̪ ɒ v]
* juvon:
[d͡ʒ u v ɒ n]
* ovqat:
[ɒ v q a t̪]
Occurrences:
44
Examples:
* shaxs:
[ʃ a χ s]
* taxta:
[t̪ a χ t̪ a]
* xunuk:
[χ u n u k]
* xalq:
[χ a l q]
Occurrences:
19
Examples:
* tog':
[t̪ ɒ ʁ]
Occurrences:
70
Examples:
* hech:
[h e t͡ʃ]
* nikoh:
[n i k ɒ h]
* ham:
[h a m]
* hozir:
[h ɒ z i r]

Approximant
Occurrences:
210
Examples:
* uyni:
[u j n i]
* sinay:
[s i n a j]
* yuk:
[j u k]
* ya'ni:
[j a ʔ n i]

Trill
Occurrences:
381
Examples:
* safar:
[s a ɸ a r]
* sigir:
[s i ɡ i r]
* o'rta:
[o r t̪ a]
* biri:
[b i r i]

Lateral
Occurrences:
413
Examples:
* oltin:
[ɒ l t̪ i n]
* sol.:
[s ɒ l]
* aldov:
[a l d̪ ɒ v]
* qolib:
[q ɒ l i b]

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:
891
Examples:
* oltin:
[ɒ l t̪ i n]
* ishga:
[i ʃ ɡ a]
* uyni:
[u j n i]
* qolib:
[q ɒ l i b]
Occurrences:
181
Examples:
* mavzu:
[m a v z u]
* uyni:
[u j n i]
* buni:
[b u n i]
* uchun:
[u t͡ʃ u n]

Close-Mid
Occurrences:
133
Examples:
* hech:
[h e t͡ʃ]
* necha:
[n e t͡ʃ a]
* dedi:
[d̪ e d̪ i]
* emas,:
[e m a s]
Occurrences:
103
Examples:
* o'n:
[o n]
* so'm:
[s o m]
* o'rta:
[o r t̪ a]
* o'ch:
[o t͡ʃ]

Open-Mid

Open
Occurrences:
1,015
Examples:
* ishga:
[i ʃ ɡ a]
* mavzu:
[m a v z u]
* safar:
[s a ɸ a r]
* aldov:
[a l d̪ ɒ v]
Occurrences:
369
Examples:
* oltin:
[ɒ l t̪ i n]
* sof:
[s ɒ ɸ]
* dod:
[d̪ ɒ d̪]
* sol.:
[s ɒ l]
On this page
Show Source