FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3171699967> ?p ?o ?g. }

• W3171699967 abstract "Linguistic tone is transcribed for input into ASR systems in numerous ways. This paper shows a systematic test of several transcription styles, using as an example the Chibchan language Bribri, an extremely low-resource language from Costa Rica. The most successful models separate the tone from the vowel, so that the ASR algorithms learn tone patterns independently. These models showed improvements ranging from 4% to 25% in character error rate (CER), and between 3% and 23% in word error rate (WER). This is true for both traditional GMM/HMM and end-to-end CTC algorithms. This paper also presents the first attempt to train ASR models for Bribri. The best performing models had a CER of 33% and a WER of 50%. Despite the disadvantage of using hand-engineered representations, these models were trained on only 68 minutes of data, and therefore show the potential of ASR to generate further training materials and aid in the documentation and revitalization of the language." @default.
• W3171699967 created "2021-06-22" @default.
• W3171699967 creator A5088969046 @default.
• W3171699967 date "2021-01-01" @default.
• W3171699967 modified "2023-09-23" @default.
• W3171699967 title "Explicit Tone Transcription Improves ASR Performance in Extremely Low-Resource Languages: A Case Study in Bribri" @default.
• W3171699967 cites W108550785 @default.
• W3171699967 cites W1506312643 @default.
• W3171699967 cites W1524333225 @default.
• W3171699967 cites W1922655562 @default.
• W3171699967 cites W2018997872 @default.
• W3171699967 cites W2025689458 @default.
• W3171699967 cites W2038784064 @default.
• W3171699967 cites W2040083284 @default.
• W3171699967 cites W2048804461 @default.
• W3171699967 cites W2066824132 @default.
• W3171699967 cites W2087395764 @default.
• W3171699967 cites W2091746061 @default.
• W3171699967 cites W2094291475 @default.
• W3171699967 cites W2109726413 @default.
• W3171699967 cites W2127141656 @default.
• W3171699967 cites W2134800885 @default.
• W3171699967 cites W2169170859 @default.
• W3171699967 cites W2294256115 @default.
• W3171699967 cites W2327501763 @default.
• W3171699967 cites W2346634343 @default.
• W3171699967 cites W2399924864 @default.
• W3171699967 cites W2557283755 @default.
• W3171699967 cites W2571791129 @default.
• W3171699967 cites W2603738274 @default.
• W3171699967 cites W2610432213 @default.
• W3171699967 cites W2748437391 @default.
• W3171699967 cites W2787760419 @default.
• W3171699967 cites W2806339485 @default.
• W3171699967 cites W2806868664 @default.
• W3171699967 cites W2893647263 @default.
• W3171699967 cites W2895097770 @default.
• W3171699967 cites W2905095391 @default.
• W3171699967 cites W2962804563 @default.
• W3171699967 cites W2963303951 @default.
• W3171699967 cites W2963431393 @default.
• W3171699967 cites W2963522845 @default.
• W3171699967 cites W2972520202 @default.
• W3171699967 cites W2992384298 @default.
• W3171699967 cites W3007243649 @default.
• W3171699967 cites W3015877095 @default.
• W3171699967 cites W3016035312 @default.
• W3171699967 cites W3017221758 @default.
• W3171699967 cites W3018013522 @default.
• W3171699967 cites W3027428931 @default.
• W3171699967 cites W3028846133 @default.
• W3171699967 cites W3029693316 @default.
• W3171699967 cites W3030509225 @default.
• W3171699967 cites W3035485128 @default.
• W3171699967 cites W3084713055 @default.
• W3171699967 cites W3087775410 @default.
• W3171699967 cites W3099782249 @default.
• W3171699967 cites W3121571501 @default.
• W3171699967 cites W3135295080 @default.
• W3171699967 cites W3162144650 @default.
• W3171699967 cites W48800498 @default.
• W3171699967 cites W592849009 @default.
• W3171699967 cites W643936199 @default.
• W3171699967 cites W73665476 @default.
• W3171699967 cites W1966015606 @default.
• W3171699967 doi "https://doi.org/10.18653/v1/2021.americasnlp-1.20" @default.
• W3171699967 hasPublicationYear "2021" @default.
• W3171699967 type Work @default.
• W3171699967 sameAs 3171699967 @default.
• W3171699967 citedByCount "1" @default.
• W3171699967 countsByYear W31716999672022 @default.
• W3171699967 crossrefType "proceedings-article" @default.
• W3171699967 hasAuthorship W3171699967A5088969046 @default.
• W3171699967 hasBestOaLocation W31716999671 @default.
• W3171699967 hasConcept C137293760 @default.
• W3171699967 hasConcept C138885662 @default.
• W3171699967 hasConcept C154945302 @default.
• W3171699967 hasConcept C179926584 @default.
• W3171699967 hasConcept C199360897 @default.
• W3171699967 hasConcept C204321447 @default.
• W3171699967 hasConcept C23224414 @default.
• W3171699967 hasConcept C2524010 @default.
• W3171699967 hasConcept C2779581591 @default.
• W3171699967 hasConcept C2780583480 @default.
• W3171699967 hasConcept C2780861071 @default.
• W3171699967 hasConcept C28490314 @default.
• W3171699967 hasConcept C33923547 @default.
• W3171699967 hasConcept C40969351 @default.
• W3171699967 hasConcept C41008148 @default.
• W3171699967 hasConcept C41895202 @default.
• W3171699967 hasConcept C56666940 @default.
• W3171699967 hasConcept C90805587 @default.
• W3171699967 hasConceptScore W3171699967C137293760 @default.
• W3171699967 hasConceptScore W3171699967C138885662 @default.
• W3171699967 hasConceptScore W3171699967C154945302 @default.
• W3171699967 hasConceptScore W3171699967C179926584 @default.
• W3171699967 hasConceptScore W3171699967C199360897 @default.
• W3171699967 hasConceptScore W3171699967C204321447 @default.
• W3171699967 hasConceptScore W3171699967C23224414 @default.
• W3171699967 hasConceptScore W3171699967C2524010 @default.

• next