FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385655423> ?p ?o ?g. }

• W4385655423 endingPage "9062" @default.
• W4385655423 startingPage "9062" @default.
• W4385655423 abstract "Speech Emotion Recognition (SER) plays a crucial role in applications involving human-machine interaction. However, the scarcity of suitable emotional speech datasets presents a major challenge for accurate SER systems. Deep Neural Network (DNN)-based solutions currently in use require substantial labelled data for successful training. Previous studies have proposed strategies to expand the training set in this framework by leveraging available emotion speech corpora. This paper assesses the impact of a cross-corpus training extension for a SER system using self-supervised (SS) representations, namely HuBERT and WavLM. The feasibility of training systems with just a few minutes of in-domain audio is also analyzed. The experimental results demonstrate that augmenting the training set with EmoDB (German), RAVDESS, and CREMA-D (English) datasets leads to improved SER accuracy on the IEMOCAP dataset. By combining a cross-corpus training extension and SS representations, state-of-the-art performance is achieved. These findings suggest that the cross-corpus strategy effectively addresses the scarcity of labelled data and enhances the performance of SER systems." @default.
• W4385655423 created "2023-08-09" @default.
• W4385655423 creator A5020174874 @default.
• W4385655423 creator A5020467262 @default.
• W4385655423 creator A5036493563 @default.
• W4385655423 creator A5054254044 @default.
• W4385655423 creator A5066085685 @default.
• W4385655423 date "2023-08-08" @default.
• W4385655423 modified "2023-10-02" @default.
• W4385655423 title "Cross-Corpus Training Strategy for Speech Emotion Recognition Using Self-Supervised Representations" @default.
• W4385655423 cites W175750906 @default.
• W4385655423 cites W2030931454 @default.
• W4385655423 cites W2146334809 @default.
• W4385655423 cites W2149628368 @default.
• W4385655423 cites W2239141610 @default.
• W4385655423 cites W2322208196 @default.
• W4385655423 cites W2397175282 @default.
• W4385655423 cites W2498787287 @default.
• W4385655423 cites W2802656254 @default.
• W4385655423 cites W2951442257 @default.
• W4385655423 cites W3096918678 @default.
• W4385655423 cites W3120709499 @default.
• W4385655423 cites W3197580070 @default.
• W4385655423 cites W3209059054 @default.
• W4385655423 cites W3209984917 @default.
• W4385655423 cites W4210505096 @default.
• W4385655423 cites W4281633243 @default.
• W4385655423 cites W4282558231 @default.
• W4385655423 cites W4308521113 @default.
• W4385655423 doi "https://doi.org/10.3390/app13169062" @default.
• W4385655423 hasPublicationYear "2023" @default.
• W4385655423 type Work @default.
• W4385655423 citedByCount "1" @default.
• W4385655423 countsByYear W43856554232023 @default.
• W4385655423 crossrefType "journal-article" @default.
• W4385655423 hasAuthorship W4385655423A5020174874 @default.
• W4385655423 hasAuthorship W4385655423A5020467262 @default.
• W4385655423 hasAuthorship W4385655423A5036493563 @default.
• W4385655423 hasAuthorship W4385655423A5054254044 @default.
• W4385655423 hasAuthorship W4385655423A5066085685 @default.
• W4385655423 hasBestOaLocation W43856554231 @default.
• W4385655423 hasConcept C109747225 @default.
• W4385655423 hasConcept C119857082 @default.
• W4385655423 hasConcept C121332964 @default.
• W4385655423 hasConcept C134306372 @default.
• W4385655423 hasConcept C153294291 @default.
• W4385655423 hasConcept C154945302 @default.
• W4385655423 hasConcept C162324750 @default.
• W4385655423 hasConcept C175444787 @default.
• W4385655423 hasConcept C177264268 @default.
• W4385655423 hasConcept C199360897 @default.
• W4385655423 hasConcept C204321447 @default.
• W4385655423 hasConcept C2776145971 @default.
• W4385655423 hasConcept C2777211547 @default.
• W4385655423 hasConcept C2777438025 @default.
• W4385655423 hasConcept C2778029271 @default.
• W4385655423 hasConcept C28490314 @default.
• W4385655423 hasConcept C2984842247 @default.
• W4385655423 hasConcept C33923547 @default.
• W4385655423 hasConcept C36503486 @default.
• W4385655423 hasConcept C41008148 @default.
• W4385655423 hasConcept C50644808 @default.
• W4385655423 hasConcept C51632099 @default.
• W4385655423 hasConceptScore W4385655423C109747225 @default.
• W4385655423 hasConceptScore W4385655423C119857082 @default.
• W4385655423 hasConceptScore W4385655423C121332964 @default.
• W4385655423 hasConceptScore W4385655423C134306372 @default.
• W4385655423 hasConceptScore W4385655423C153294291 @default.
• W4385655423 hasConceptScore W4385655423C154945302 @default.
• W4385655423 hasConceptScore W4385655423C162324750 @default.
• W4385655423 hasConceptScore W4385655423C175444787 @default.
• W4385655423 hasConceptScore W4385655423C177264268 @default.
• W4385655423 hasConceptScore W4385655423C199360897 @default.
• W4385655423 hasConceptScore W4385655423C204321447 @default.
• W4385655423 hasConceptScore W4385655423C2776145971 @default.
• W4385655423 hasConceptScore W4385655423C2777211547 @default.
• W4385655423 hasConceptScore W4385655423C2777438025 @default.
• W4385655423 hasConceptScore W4385655423C2778029271 @default.
• W4385655423 hasConceptScore W4385655423C28490314 @default.
• W4385655423 hasConceptScore W4385655423C2984842247 @default.
• W4385655423 hasConceptScore W4385655423C33923547 @default.
• W4385655423 hasConceptScore W4385655423C36503486 @default.
• W4385655423 hasConceptScore W4385655423C41008148 @default.
• W4385655423 hasConceptScore W4385655423C50644808 @default.
• W4385655423 hasConceptScore W4385655423C51632099 @default.
• W4385655423 hasFunder F4320320300 @default.
• W4385655423 hasIssue "16" @default.
• W4385655423 hasLocation W43856554231 @default.
• W4385655423 hasOpenAccess W4385655423 @default.
• W4385655423 hasPrimaryLocation W43856554231 @default.
• W4385655423 hasRelatedWork W2166162971 @default.
• W4385655423 hasRelatedWork W2352907195 @default.
• W4385655423 hasRelatedWork W2760234924 @default.
• W4385655423 hasRelatedWork W2949092679 @default.
• W4385655423 hasRelatedWork W3093533780 @default.
• W4385655423 hasRelatedWork W3144173820 @default.
• W4385655423 hasRelatedWork W3160525311 @default.
• W4385655423 hasRelatedWork W3201070945 @default.

• next