Matches in SemOpenAlex for { <https://semopenalex.org/work/W2788486293> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2788486293 abstract "Developing speech technologies for low-resource languages has become a very active research field over the last decade. Among others, Bayesian models have shown some promising results on artificial examples but still lack of in situ experiments. Our work applies state-of-the-art Bayesian models to unsupervised Acoustic Unit Discovery (AUD) in a real low-resource language scenario. We also show that Bayesian models can naturally integrate information from other resourceful languages by means of informative prior leading to more consistent discovered units. Finally, discovered acoustic units are used, either as the 1-best sequence or as a lattice, to perform word segmentation. Word segmentation results show that this Bayesian approach clearly outperforms a Segmental-DTW baseline on the same corpus." @default.
- W2788486293 created "2018-03-06" @default.
- W2788486293 creator A5001668256 @default.
- W2788486293 creator A5004778663 @default.
- W2788486293 creator A5007620149 @default.
- W2788486293 creator A5014580424 @default.
- W2788486293 creator A5030615769 @default.
- W2788486293 creator A5040820339 @default.
- W2788486293 creator A5042273299 @default.
- W2788486293 creator A5048860892 @default.
- W2788486293 creator A5061249946 @default.
- W2788486293 creator A5073641618 @default.
- W2788486293 date "2018-04-19" @default.
- W2788486293 modified "2023-10-09" @default.
- W2788486293 title "Bayesian models for unit discovery on a very low resource language" @default.
- W2788486293 cites W1506806321 @default.
- W2788486293 cites W1833498382 @default.
- W2788486293 cites W2033413759 @default.
- W2788486293 cites W2100768664 @default.
- W2788486293 cites W2142390309 @default.
- W2788486293 cites W2166851633 @default.
- W2788486293 cites W2251025892 @default.
- W2788486293 cites W2345799635 @default.
- W2788486293 cites W2347098582 @default.
- W2788486293 cites W2347145335 @default.
- W2788486293 cites W2464234964 @default.
- W2788486293 cites W2564058731 @default.
- W2788486293 cites W2641832364 @default.
- W2788486293 cites W2719865699 @default.
- W2788486293 cites W2762715843 @default.
- W2788486293 cites W2951004968 @default.
- W2788486293 hasPublicationYear "2018" @default.
- W2788486293 type Work @default.
- W2788486293 sameAs 2788486293 @default.
- W2788486293 citedByCount "2" @default.
- W2788486293 countsByYear W27884862932018 @default.
- W2788486293 countsByYear W27884862932019 @default.
- W2788486293 crossrefType "proceedings-article" @default.
- W2788486293 hasAuthorship W2788486293A5001668256 @default.
- W2788486293 hasAuthorship W2788486293A5004778663 @default.
- W2788486293 hasAuthorship W2788486293A5007620149 @default.
- W2788486293 hasAuthorship W2788486293A5014580424 @default.
- W2788486293 hasAuthorship W2788486293A5030615769 @default.
- W2788486293 hasAuthorship W2788486293A5040820339 @default.
- W2788486293 hasAuthorship W2788486293A5042273299 @default.
- W2788486293 hasAuthorship W2788486293A5048860892 @default.
- W2788486293 hasAuthorship W2788486293A5061249946 @default.
- W2788486293 hasAuthorship W2788486293A5073641618 @default.
- W2788486293 hasBestOaLocation W27884862931 @default.
- W2788486293 hasConcept C107673813 @default.
- W2788486293 hasConcept C122637931 @default.
- W2788486293 hasConcept C137293760 @default.
- W2788486293 hasConcept C145420912 @default.
- W2788486293 hasConcept C154945302 @default.
- W2788486293 hasConcept C204321447 @default.
- W2788486293 hasConcept C206345919 @default.
- W2788486293 hasConcept C31258907 @default.
- W2788486293 hasConcept C33923547 @default.
- W2788486293 hasConcept C41008148 @default.
- W2788486293 hasConceptScore W2788486293C107673813 @default.
- W2788486293 hasConceptScore W2788486293C122637931 @default.
- W2788486293 hasConceptScore W2788486293C137293760 @default.
- W2788486293 hasConceptScore W2788486293C145420912 @default.
- W2788486293 hasConceptScore W2788486293C154945302 @default.
- W2788486293 hasConceptScore W2788486293C204321447 @default.
- W2788486293 hasConceptScore W2788486293C206345919 @default.
- W2788486293 hasConceptScore W2788486293C31258907 @default.
- W2788486293 hasConceptScore W2788486293C33923547 @default.
- W2788486293 hasConceptScore W2788486293C41008148 @default.
- W2788486293 hasLocation W27884862931 @default.
- W2788486293 hasLocation W27884862932 @default.
- W2788486293 hasLocation W27884862933 @default.
- W2788486293 hasLocation W27884862934 @default.
- W2788486293 hasLocation W27884862935 @default.
- W2788486293 hasOpenAccess W2788486293 @default.
- W2788486293 hasPrimaryLocation W27884862931 @default.
- W2788486293 hasRelatedWork W1509983653 @default.
- W2788486293 hasRelatedWork W1556748146 @default.
- W2788486293 hasRelatedWork W2371343292 @default.
- W2788486293 hasRelatedWork W3199594174 @default.
- W2788486293 hasRelatedWork W3215563689 @default.
- W2788486293 hasRelatedWork W591599671 @default.
- W2788486293 hasRelatedWork W610590827 @default.
- W2788486293 hasRelatedWork W611386996 @default.
- W2788486293 hasRelatedWork W617685022 @default.
- W2788486293 hasRelatedWork W629290331 @default.
- W2788486293 isParatext "false" @default.
- W2788486293 isRetracted "false" @default.
- W2788486293 magId "2788486293" @default.
- W2788486293 workType "article" @default.