Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226209037> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4226209037 abstract "The high cost of data acquisition makes Automatic Speech Recognition (ASR) model training problematic for most existing languages, including languages that do not even have a written script, or for which the phone inventories remain unknown. Past works explored multilingual training, transfer learning, as well as zero-shot learning in order to build ASR systems for these low-resource languages. While it has been shown that the pooling of resources from multiple languages is helpful, we have not yet seen a successful application of an ASR model to a language unseen during training. A crucial step in the adaptation of ASR from seen to unseen languages is the creation of the phone inventory of the unseen language. The ultimate goal of our work is to build the phone inventory of a language unseen during training in an unsupervised way without any knowledge about the language. In this paper, we 1) investigate the influence of different factors (i.e., model architecture, phonotactic model, type of speech representation) on phone recognition in an unknown language; 2) provide an analysis of which phones transfer well across languages and which do not in order to understand the limitations of and areas for further improvement for automatic phone inventory creation; and 3) present different methods to build a phone inventory of an unseen language in an unsupervised way. To that end, we conducted mono-, multi-, and crosslingual experiments on a set of 13 phonetically diverse languages and several in-depth analyses. We found a number of universal phone tokens (IPA symbols) that are well-recognized cross-linguistically. Through a detailed analysis of results, we conclude that unique sounds, similar sounds, and tone languages remain a major challenge for phonetic inventory discovery." @default.
- W4226209037 created "2022-05-05" @default.
- W4226209037 creator A5004778663 @default.
- W4226209037 creator A5027217976 @default.
- W4226209037 creator A5045247662 @default.
- W4226209037 creator A5048860892 @default.
- W4226209037 creator A5050632169 @default.
- W4226209037 creator A5053373302 @default.
- W4226209037 creator A5062172410 @default.
- W4226209037 creator A5069488212 @default.
- W4226209037 date "2022-01-26" @default.
- W4226209037 modified "2023-10-12" @default.
- W4226209037 title "Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition" @default.
- W4226209037 doi "https://doi.org/10.48550/arxiv.2201.11207" @default.
- W4226209037 hasPublicationYear "2022" @default.
- W4226209037 type Work @default.
- W4226209037 citedByCount "0" @default.
- W4226209037 crossrefType "posted-content" @default.
- W4226209037 hasAuthorship W4226209037A5004778663 @default.
- W4226209037 hasAuthorship W4226209037A5027217976 @default.
- W4226209037 hasAuthorship W4226209037A5045247662 @default.
- W4226209037 hasAuthorship W4226209037A5048860892 @default.
- W4226209037 hasAuthorship W4226209037A5050632169 @default.
- W4226209037 hasAuthorship W4226209037A5053373302 @default.
- W4226209037 hasAuthorship W4226209037A5062172410 @default.
- W4226209037 hasAuthorship W4226209037A5069488212 @default.
- W4226209037 hasBestOaLocation W42262090371 @default.
- W4226209037 hasConcept C137293760 @default.
- W4226209037 hasConcept C138885662 @default.
- W4226209037 hasConcept C148934300 @default.
- W4226209037 hasConcept C150899416 @default.
- W4226209037 hasConcept C154945302 @default.
- W4226209037 hasConcept C204321447 @default.
- W4226209037 hasConcept C2778707766 @default.
- W4226209037 hasConcept C28490314 @default.
- W4226209037 hasConcept C41008148 @default.
- W4226209037 hasConcept C41895202 @default.
- W4226209037 hasConcept C4768521 @default.
- W4226209037 hasConcept C70437156 @default.
- W4226209037 hasConceptScore W4226209037C137293760 @default.
- W4226209037 hasConceptScore W4226209037C138885662 @default.
- W4226209037 hasConceptScore W4226209037C148934300 @default.
- W4226209037 hasConceptScore W4226209037C150899416 @default.
- W4226209037 hasConceptScore W4226209037C154945302 @default.
- W4226209037 hasConceptScore W4226209037C204321447 @default.
- W4226209037 hasConceptScore W4226209037C2778707766 @default.
- W4226209037 hasConceptScore W4226209037C28490314 @default.
- W4226209037 hasConceptScore W4226209037C41008148 @default.
- W4226209037 hasConceptScore W4226209037C41895202 @default.
- W4226209037 hasConceptScore W4226209037C4768521 @default.
- W4226209037 hasConceptScore W4226209037C70437156 @default.
- W4226209037 hasLocation W42262090371 @default.
- W4226209037 hasOpenAccess W4226209037 @default.
- W4226209037 hasPrimaryLocation W42262090371 @default.
- W4226209037 hasRelatedWork W2003136674 @default.
- W4226209037 hasRelatedWork W2100357249 @default.
- W4226209037 hasRelatedWork W2105189960 @default.
- W4226209037 hasRelatedWork W2171933535 @default.
- W4226209037 hasRelatedWork W2188087548 @default.
- W4226209037 hasRelatedWork W2975191379 @default.
- W4226209037 hasRelatedWork W3107474891 @default.
- W4226209037 hasRelatedWork W4211116738 @default.
- W4226209037 hasRelatedWork W4220989776 @default.
- W4226209037 hasRelatedWork W4226209037 @default.
- W4226209037 isParatext "false" @default.
- W4226209037 isRetracted "false" @default.
- W4226209037 workType "article" @default.