FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4211116738> ?p ?o ?g. }

• W4211116738 endingPage "101358" @default.
• W4211116738 startingPage "101358" @default.
• W4211116738 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.
• W4211116738 created "2022-02-13" @default.
• W4211116738 creator A5004778663 @default.
• W4211116738 creator A5027217976 @default.
• W4211116738 creator A5045247662 @default.
• W4211116738 creator A5048860892 @default.
• W4211116738 creator A5050632169 @default.
• W4211116738 creator A5053373302 @default.
• W4211116738 creator A5062172410 @default.
• W4211116738 creator A5069488212 @default.
• W4211116738 date "2022-07-01" @default.
• W4211116738 modified "2023-10-12" @default.
• W4211116738 title "Discovering phonetic inventories with crosslingual automatic speech recognition" @default.
• W4211116738 cites W1436754857 @default.
• W4211116738 cites W1577418252 @default.
• W4211116738 cites W1631260214 @default.
• W4211116738 cites W1778492285 @default.
• W4211116738 cites W1796128977 @default.
• W4211116738 cites W1964917299 @default.
• W4211116738 cites W1968147312 @default.
• W4211116738 cites W1970890968 @default.
• W4211116738 cites W1978352171 @default.
• W4211116738 cites W1993799394 @default.
• W4211116738 cites W2006617198 @default.
• W4211116738 cites W2025198378 @default.
• W4211116738 cites W2033436836 @default.
• W4211116738 cites W2041252889 @default.
• W4211116738 cites W2046932483 @default.
• W4211116738 cites W2077804127 @default.
• W4211116738 cites W2078769636 @default.
• W4211116738 cites W2079623482 @default.
• W4211116738 cites W2079641914 @default.
• W4211116738 cites W2108776455 @default.
• W4211116738 cites W2120209245 @default.
• W4211116738 cites W2127141656 @default.
• W4211116738 cites W2156483112 @default.
• W4211116738 cites W2295676751 @default.
• W4211116738 cites W2317002935 @default.
• W4211116738 cites W2317579269 @default.
• W4211116738 cites W2319623048 @default.
• W4211116738 cites W2321675883 @default.
• W4211116738 cites W2332939288 @default.
• W4211116738 cites W2400517318 @default.
• W4211116738 cites W2401430117 @default.
• W4211116738 cites W2402366697 @default.
• W4211116738 cites W2412593044 @default.
• W4211116738 cites W2509930204 @default.
• W4211116738 cites W2511875134 @default.
• W4211116738 cites W2514741789 @default.
• W4211116738 cites W2739883972 @default.
• W4211116738 cites W2747192917 @default.
• W4211116738 cites W2749648329 @default.
• W4211116738 cites W2750248772 @default.
• W4211116738 cites W2754396191 @default.
• W4211116738 cites W2785860501 @default.
• W4211116738 cites W2786608204 @default.
• W4211116738 cites W2787223168 @default.
• W4211116738 cites W2787426069 @default.
• W4211116738 cites W2791647162 @default.
• W4211116738 cites W2826003142 @default.
• W4211116738 cites W2888867175 @default.
• W4211116738 cites W2889326414 @default.
• W4211116738 cites W2891816510 @default.
• W4211116738 cites W2962780374 @default.
• W4211116738 cites W2971840980 @default.
• W4211116738 cites W2972374322 @default.
• W4211116738 cites W2972764223 @default.
• W4211116738 cites W2973026522 @default.
• W4211116738 cites W3005578234 @default.
• W4211116738 cites W3007826012 @default.
• W4211116738 cites W3015877095 @default.
• W4211116738 cites W3016010032 @default.
• W4211116738 cites W308497914 @default.
• W4211116738 cites W3095732712 @default.
• W4211116738 cites W3105242324 @default.
• W4211116738 cites W3196459653 @default.
• W4211116738 cites W4240842827 @default.
• W4211116738 cites W4249993336 @default.
• W4211116738 cites W2586754519 @default.
• W4211116738 doi "https://doi.org/10.1016/j.csl.2022.101358" @default.
• W4211116738 hasPublicationYear "2022" @default.
• W4211116738 type Work @default.
• W4211116738 citedByCount "4" @default.
• W4211116738 countsByYear W42111167382022 @default.
• W4211116738 countsByYear W42111167382023 @default.
• W4211116738 crossrefType "journal-article" @default.
• W4211116738 hasAuthorship W4211116738A5004778663 @default.
• W4211116738 hasAuthorship W4211116738A5027217976 @default.
• W4211116738 hasAuthorship W4211116738A5045247662 @default.
• W4211116738 hasAuthorship W4211116738A5048860892 @default.
• W4211116738 hasAuthorship W4211116738A5050632169 @default.
• W4211116738 hasAuthorship W4211116738A5053373302 @default.
• W4211116738 hasAuthorship W4211116738A5062172410 @default.
• W4211116738 hasAuthorship W4211116738A5069488212 @default.
• W4211116738 hasBestOaLocation W42111167381 @default.
• W4211116738 hasConcept C137293760 @default.
• W4211116738 hasConcept C138885662 @default.
• W4211116738 hasConcept C148934300 @default.

• next