Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285136062> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4285136062 abstract "Transcription is often reported as the bottleneck in endangered language documentation, requiring large efforts from scarce speakers and transcribers. In general, automatic speech recognition (ASR) can be accurate enough to accelerate transcription only if trained on large amounts of transcribed data. However, when a single speaker is involved, several studies have reported encouraging results for phonetic transcription even with small amounts of training. Here we expand this body of work on speaker-dependent transcription by comparing four ASR approaches, notably recent transformer and pretrained multilingual models, on a common dataset of 11 languages. To automate data preparation, training and evaluation steps, we also developed a phoneme recognition setup which handles morphologically complex languages and writing systems for which no pronunciation dictionary exists.We find that fine-tuning a multilingual pretrained model yields an average phoneme error rate (PER) of 15% for 6 languages with 99 minutes or less of transcribed data for training. For the 5 languages with between 100 and 192 minutes of training, we achieved a PER of 8.4% or less. These results on a number of varied languages suggest that ASR can now significantly reduce transcription efforts in the speaker-dependent situation common in endangered language work." @default.
- W4285136062 created "2022-07-14" @default.
- W4285136062 creator A5079352923 @default.
- W4285136062 date "2022-01-01" @default.
- W4285136062 modified "2023-10-18" @default.
- W4285136062 title "Phoneme transcription of endangered languages: an evaluation of recent ASR architectures in the single speaker scenario" @default.
- W4285136062 doi "https://doi.org/10.18653/v1/2022.findings-acl.180" @default.
- W4285136062 hasPublicationYear "2022" @default.
- W4285136062 type Work @default.
- W4285136062 citedByCount "0" @default.
- W4285136062 crossrefType "proceedings-article" @default.
- W4285136062 hasAuthorship W4285136062A5079352923 @default.
- W4285136062 hasBestOaLocation W42851360621 @default.
- W4285136062 hasConcept C119599485 @default.
- W4285136062 hasConcept C127413603 @default.
- W4285136062 hasConcept C137293760 @default.
- W4285136062 hasConcept C138885662 @default.
- W4285136062 hasConcept C149635348 @default.
- W4285136062 hasConcept C154945302 @default.
- W4285136062 hasConcept C165801399 @default.
- W4285136062 hasConcept C179926584 @default.
- W4285136062 hasConcept C204321447 @default.
- W4285136062 hasConcept C2780513914 @default.
- W4285136062 hasConcept C2780844864 @default.
- W4285136062 hasConcept C28490314 @default.
- W4285136062 hasConcept C40969351 @default.
- W4285136062 hasConcept C41008148 @default.
- W4285136062 hasConcept C41895202 @default.
- W4285136062 hasConcept C66322947 @default.
- W4285136062 hasConceptScore W4285136062C119599485 @default.
- W4285136062 hasConceptScore W4285136062C127413603 @default.
- W4285136062 hasConceptScore W4285136062C137293760 @default.
- W4285136062 hasConceptScore W4285136062C138885662 @default.
- W4285136062 hasConceptScore W4285136062C149635348 @default.
- W4285136062 hasConceptScore W4285136062C154945302 @default.
- W4285136062 hasConceptScore W4285136062C165801399 @default.
- W4285136062 hasConceptScore W4285136062C179926584 @default.
- W4285136062 hasConceptScore W4285136062C204321447 @default.
- W4285136062 hasConceptScore W4285136062C2780513914 @default.
- W4285136062 hasConceptScore W4285136062C2780844864 @default.
- W4285136062 hasConceptScore W4285136062C28490314 @default.
- W4285136062 hasConceptScore W4285136062C40969351 @default.
- W4285136062 hasConceptScore W4285136062C41008148 @default.
- W4285136062 hasConceptScore W4285136062C41895202 @default.
- W4285136062 hasConceptScore W4285136062C66322947 @default.
- W4285136062 hasLocation W42851360621 @default.
- W4285136062 hasOpenAccess W4285136062 @default.
- W4285136062 hasPrimaryLocation W42851360621 @default.
- W4285136062 hasRelatedWork W139627991 @default.
- W4285136062 hasRelatedWork W1493946344 @default.
- W4285136062 hasRelatedWork W2008308193 @default.
- W4285136062 hasRelatedWork W2235458433 @default.
- W4285136062 hasRelatedWork W2399356099 @default.
- W4285136062 hasRelatedWork W2401572723 @default.
- W4285136062 hasRelatedWork W2475014315 @default.
- W4285136062 hasRelatedWork W2485759381 @default.
- W4285136062 hasRelatedWork W2563850823 @default.
- W4285136062 hasRelatedWork W3193318782 @default.
- W4285136062 isParatext "false" @default.
- W4285136062 isRetracted "false" @default.
- W4285136062 workType "article" @default.