Matches in SemOpenAlex for { <https://semopenalex.org/work/W2901849296> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2901849296 abstract "Many people are suffering from voice disorders, which can adversely affect the quality of their lives. In response, some researchers have proposed algorithms for automatic assessment of these disorders, based on voice signals. However, these signals can be sensitive to the recording devices. Indeed, the channel effect is a pervasive problem in machine learning for healthcare. In this study, we propose a detection system for pathological voice, which is robust against the channel effect. This system is based on a bidirectional LSTM network. To increase the performance robustness against channel mismatch, we integrate domain adversarial training (DAT) to eliminate the differences between the devices. When we train on data recorded on a high-quality microphone and evaluate on smartphone data without labels, our robust detection system increases the PR-AUC from 0.8448 to 0.9455 (and 0.9522 with target sample labels). To the best of our knowledge, this is the first study applying unsupervised domain adaptation to pathological voice detection. Notably, our system does not need target device sample labels, which allows for generalization to many new devices." @default.
- W2901849296 created "2018-11-29" @default.
- W2901849296 creator A5024250477 @default.
- W2901849296 creator A5036364468 @default.
- W2901849296 creator A5036703722 @default.
- W2901849296 creator A5038450527 @default.
- W2901849296 creator A5044008055 @default.
- W2901849296 creator A5056256317 @default.
- W2901849296 date "2018-11-26" @default.
- W2901849296 modified "2023-10-16" @default.
- W2901849296 title "Robustness against the channel effect in pathological voice detection" @default.
- W2901849296 cites W1598514414 @default.
- W2901849296 cites W2056981279 @default.
- W2901849296 cites W2162109146 @default.
- W2901849296 cites W2170509092 @default.
- W2901849296 cites W2404317780 @default.
- W2901849296 cites W2791062765 @default.
- W2901849296 cites W2883781843 @default.
- W2901849296 cites W84813673 @default.
- W2901849296 doi "https://doi.org/10.48550/arxiv.1811.10376" @default.
- W2901849296 hasPublicationYear "2018" @default.
- W2901849296 type Work @default.
- W2901849296 sameAs 2901849296 @default.
- W2901849296 citedByCount "0" @default.
- W2901849296 crossrefType "posted-content" @default.
- W2901849296 hasAuthorship W2901849296A5024250477 @default.
- W2901849296 hasAuthorship W2901849296A5036364468 @default.
- W2901849296 hasAuthorship W2901849296A5036703722 @default.
- W2901849296 hasAuthorship W2901849296A5038450527 @default.
- W2901849296 hasAuthorship W2901849296A5044008055 @default.
- W2901849296 hasAuthorship W2901849296A5056256317 @default.
- W2901849296 hasBestOaLocation W29018492961 @default.
- W2901849296 hasConcept C104317684 @default.
- W2901849296 hasConcept C119857082 @default.
- W2901849296 hasConcept C127162648 @default.
- W2901849296 hasConcept C134306372 @default.
- W2901849296 hasConcept C154945302 @default.
- W2901849296 hasConcept C177148314 @default.
- W2901849296 hasConcept C185592680 @default.
- W2901849296 hasConcept C204201278 @default.
- W2901849296 hasConcept C2776434776 @default.
- W2901849296 hasConcept C2778263558 @default.
- W2901849296 hasConcept C28490314 @default.
- W2901849296 hasConcept C31258907 @default.
- W2901849296 hasConcept C33923547 @default.
- W2901849296 hasConcept C41008148 @default.
- W2901849296 hasConcept C55493867 @default.
- W2901849296 hasConcept C61328038 @default.
- W2901849296 hasConcept C63479239 @default.
- W2901849296 hasConcept C68115822 @default.
- W2901849296 hasConcept C76155785 @default.
- W2901849296 hasConcept C95623464 @default.
- W2901849296 hasConceptScore W2901849296C104317684 @default.
- W2901849296 hasConceptScore W2901849296C119857082 @default.
- W2901849296 hasConceptScore W2901849296C127162648 @default.
- W2901849296 hasConceptScore W2901849296C134306372 @default.
- W2901849296 hasConceptScore W2901849296C154945302 @default.
- W2901849296 hasConceptScore W2901849296C177148314 @default.
- W2901849296 hasConceptScore W2901849296C185592680 @default.
- W2901849296 hasConceptScore W2901849296C204201278 @default.
- W2901849296 hasConceptScore W2901849296C2776434776 @default.
- W2901849296 hasConceptScore W2901849296C2778263558 @default.
- W2901849296 hasConceptScore W2901849296C28490314 @default.
- W2901849296 hasConceptScore W2901849296C31258907 @default.
- W2901849296 hasConceptScore W2901849296C33923547 @default.
- W2901849296 hasConceptScore W2901849296C41008148 @default.
- W2901849296 hasConceptScore W2901849296C55493867 @default.
- W2901849296 hasConceptScore W2901849296C61328038 @default.
- W2901849296 hasConceptScore W2901849296C63479239 @default.
- W2901849296 hasConceptScore W2901849296C68115822 @default.
- W2901849296 hasConceptScore W2901849296C76155785 @default.
- W2901849296 hasConceptScore W2901849296C95623464 @default.
- W2901849296 hasLocation W29018492961 @default.
- W2901849296 hasOpenAccess W2901849296 @default.
- W2901849296 hasPrimaryLocation W29018492961 @default.
- W2901849296 hasRelatedWork W1541080333 @default.
- W2901849296 hasRelatedWork W1628467322 @default.
- W2901849296 hasRelatedWork W2012540220 @default.
- W2901849296 hasRelatedWork W2098265087 @default.
- W2901849296 hasRelatedWork W2106462793 @default.
- W2901849296 hasRelatedWork W2122030153 @default.
- W2901849296 hasRelatedWork W2539486939 @default.
- W2901849296 hasRelatedWork W2901849296 @default.
- W2901849296 hasRelatedWork W2989932438 @default.
- W2901849296 hasRelatedWork W2889596223 @default.
- W2901849296 isParatext "false" @default.
- W2901849296 isRetracted "false" @default.
- W2901849296 magId "2901849296" @default.
- W2901849296 workType "article" @default.