Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200231323> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4200231323 endingPage "3172" @default.
- W4200231323 startingPage "3172" @default.
- W4200231323 abstract "Phonological-based features (articulatory features, AFs) describe the movements of the vocal organ which are shared across languages. This paper investigates a domain-adversarial neural network (DANN) to extract reliable AFs, and different multi-stream techniques are used for cross-lingual speech recognition. First, a novel universal phonological attributes definition is proposed for Mandarin, English, German and French. Then a DANN-based AFs detector is trained using source languages (English, German and French). When doing the cross-lingual speech recognition, the AFs detectors are used to transfer the phonological knowledge from source languages (English, German and French) to the target language (Mandarin). Two multi-stream approaches are introduced to fuse the acoustic features and cross-lingual AFs. In addition, the monolingual AFs system (i.e., the AFs are directly extracted from the target language) is also investigated. Experiments show that the performance of the AFs detector can be improved by using convolutional neural networks (CNN) with a domain-adversarial learning method. The multi-head attention (MHA) based multi-stream can reach the best performance compared to the baseline, cross-lingual adaptation approach, and other approaches. More specifically, the MHA-mode with cross-lingual AFs yields significant improvements over monolingual AFs with the restriction of training data size and, which can be easily extended to other low-resource languages." @default.
- W4200231323 created "2021-12-31" @default.
- W4200231323 creator A5021214157 @default.
- W4200231323 creator A5036437359 @default.
- W4200231323 creator A5065786740 @default.
- W4200231323 creator A5075680933 @default.
- W4200231323 creator A5078502662 @default.
- W4200231323 creator A5088732435 @default.
- W4200231323 date "2021-12-20" @default.
- W4200231323 modified "2023-10-02" @default.
- W4200231323 title "Domain-Adversarial Based Model with Phonological Knowledge for Cross-Lingual Speech Recognition" @default.
- W4200231323 cites W1979473098 @default.
- W4200231323 cites W1986174057 @default.
- W4200231323 cites W2019977809 @default.
- W4200231323 cites W2020057315 @default.
- W4200231323 cites W2039763773 @default.
- W4200231323 cites W2068447135 @default.
- W4200231323 cites W2143493821 @default.
- W4200231323 cites W2514741789 @default.
- W4200231323 cites W2560284204 @default.
- W4200231323 cites W2613787432 @default.
- W4200231323 cites W2752899488 @default.
- W4200231323 cites W2889206025 @default.
- W4200231323 cites W2889367905 @default.
- W4200231323 cites W2940111934 @default.
- W4200231323 cites W3095410713 @default.
- W4200231323 doi "https://doi.org/10.3390/electronics10243172" @default.
- W4200231323 hasPublicationYear "2021" @default.
- W4200231323 type Work @default.
- W4200231323 citedByCount "2" @default.
- W4200231323 countsByYear W42002313232022 @default.
- W4200231323 crossrefType "journal-article" @default.
- W4200231323 hasAuthorship W4200231323A5021214157 @default.
- W4200231323 hasAuthorship W4200231323A5036437359 @default.
- W4200231323 hasAuthorship W4200231323A5065786740 @default.
- W4200231323 hasAuthorship W4200231323A5075680933 @default.
- W4200231323 hasAuthorship W4200231323A5078502662 @default.
- W4200231323 hasAuthorship W4200231323A5088732435 @default.
- W4200231323 hasBestOaLocation W42002313231 @default.
- W4200231323 hasConcept C134306372 @default.
- W4200231323 hasConcept C138885662 @default.
- W4200231323 hasConcept C138954614 @default.
- W4200231323 hasConcept C154775046 @default.
- W4200231323 hasConcept C154945302 @default.
- W4200231323 hasConcept C204321447 @default.
- W4200231323 hasConcept C28490314 @default.
- W4200231323 hasConcept C33923547 @default.
- W4200231323 hasConcept C36503486 @default.
- W4200231323 hasConcept C41008148 @default.
- W4200231323 hasConcept C41895202 @default.
- W4200231323 hasConcept C81363708 @default.
- W4200231323 hasConceptScore W4200231323C134306372 @default.
- W4200231323 hasConceptScore W4200231323C138885662 @default.
- W4200231323 hasConceptScore W4200231323C138954614 @default.
- W4200231323 hasConceptScore W4200231323C154775046 @default.
- W4200231323 hasConceptScore W4200231323C154945302 @default.
- W4200231323 hasConceptScore W4200231323C204321447 @default.
- W4200231323 hasConceptScore W4200231323C28490314 @default.
- W4200231323 hasConceptScore W4200231323C33923547 @default.
- W4200231323 hasConceptScore W4200231323C36503486 @default.
- W4200231323 hasConceptScore W4200231323C41008148 @default.
- W4200231323 hasConceptScore W4200231323C41895202 @default.
- W4200231323 hasConceptScore W4200231323C81363708 @default.
- W4200231323 hasIssue "24" @default.
- W4200231323 hasLocation W42002313231 @default.
- W4200231323 hasLocation W42002313232 @default.
- W4200231323 hasLocation W42002313233 @default.
- W4200231323 hasOpenAccess W4200231323 @default.
- W4200231323 hasPrimaryLocation W42002313231 @default.
- W4200231323 hasRelatedWork W1493504683 @default.
- W4200231323 hasRelatedWork W1517743118 @default.
- W4200231323 hasRelatedWork W1887737739 @default.
- W4200231323 hasRelatedWork W1985007624 @default.
- W4200231323 hasRelatedWork W2061378985 @default.
- W4200231323 hasRelatedWork W2285788670 @default.
- W4200231323 hasRelatedWork W2748454020 @default.
- W4200231323 hasRelatedWork W2955938200 @default.
- W4200231323 hasRelatedWork W2998526951 @default.
- W4200231323 hasRelatedWork W3045684577 @default.
- W4200231323 hasVolume "10" @default.
- W4200231323 isParatext "false" @default.
- W4200231323 isRetracted "false" @default.
- W4200231323 workType "article" @default.