Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385003673> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4385003673 abstract "This paper presents a paradigm that adapts general large-scale pretrained models (PTMs) to speech emotion recognition task. Although PTMs shed new light on artificial general intelligence, they are constructed with general tasks in mind, and thus, their efficacy for specific tasks can be further improved. Additionally, employing PTMs in practical applications can be challenging due to their considerable size. Above limitations spawn another research direction, namely, optimizing large-scale PTMs for specific tasks to generate task-specific PTMs that are both compact and effective. In this paper, we focus on the speech emotion recognition task and propose an improved emotion-specific pretrained encoder called Vesper. Vesper is pretrained on a speech dataset based on WavLM and takes into account emotional characteristics. To enhance sensitivity to emotional information, Vesper employs an emotion-guided masking strategy to identify the regions that need masking. Subsequently, Vesper employs hierarchical and cross-layer self-supervision to improve its ability to capture acoustic and semantic representations, both of which are crucial for emotion recognition. Experimental results on the IEMOCAP, MELD, and CREMA-D datasets demonstrate that Vesper with 4 layers outperforms WavLM Base with 12 layers, and the performance of Vesper with 12 layers surpasses that of WavLM Large with 24 layers." @default.
- W4385003673 created "2023-07-22" @default.
- W4385003673 creator A5004837552 @default.
- W4385003673 creator A5007354180 @default.
- W4385003673 creator A5024584263 @default.
- W4385003673 creator A5036301580 @default.
- W4385003673 date "2023-07-20" @default.
- W4385003673 modified "2023-10-16" @default.
- W4385003673 title "Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition" @default.
- W4385003673 doi "https://doi.org/10.48550/arxiv.2307.10757" @default.
- W4385003673 hasPublicationYear "2023" @default.
- W4385003673 type Work @default.
- W4385003673 citedByCount "0" @default.
- W4385003673 crossrefType "posted-content" @default.
- W4385003673 hasAuthorship W4385003673A5004837552 @default.
- W4385003673 hasAuthorship W4385003673A5007354180 @default.
- W4385003673 hasAuthorship W4385003673A5024584263 @default.
- W4385003673 hasAuthorship W4385003673A5036301580 @default.
- W4385003673 hasBestOaLocation W43850036731 @default.
- W4385003673 hasConcept C111919701 @default.
- W4385003673 hasConcept C118505674 @default.
- W4385003673 hasConcept C119857082 @default.
- W4385003673 hasConcept C127413603 @default.
- W4385003673 hasConcept C142362112 @default.
- W4385003673 hasConcept C153349607 @default.
- W4385003673 hasConcept C154945302 @default.
- W4385003673 hasConcept C201995342 @default.
- W4385003673 hasConcept C204321447 @default.
- W4385003673 hasConcept C2777402240 @default.
- W4385003673 hasConcept C2780451532 @default.
- W4385003673 hasConcept C28490314 @default.
- W4385003673 hasConcept C41008148 @default.
- W4385003673 hasConceptScore W4385003673C111919701 @default.
- W4385003673 hasConceptScore W4385003673C118505674 @default.
- W4385003673 hasConceptScore W4385003673C119857082 @default.
- W4385003673 hasConceptScore W4385003673C127413603 @default.
- W4385003673 hasConceptScore W4385003673C142362112 @default.
- W4385003673 hasConceptScore W4385003673C153349607 @default.
- W4385003673 hasConceptScore W4385003673C154945302 @default.
- W4385003673 hasConceptScore W4385003673C201995342 @default.
- W4385003673 hasConceptScore W4385003673C204321447 @default.
- W4385003673 hasConceptScore W4385003673C2777402240 @default.
- W4385003673 hasConceptScore W4385003673C2780451532 @default.
- W4385003673 hasConceptScore W4385003673C28490314 @default.
- W4385003673 hasConceptScore W4385003673C41008148 @default.
- W4385003673 hasLocation W43850036731 @default.
- W4385003673 hasOpenAccess W4385003673 @default.
- W4385003673 hasPrimaryLocation W43850036731 @default.
- W4385003673 hasRelatedWork W2081647779 @default.
- W4385003673 hasRelatedWork W2275988210 @default.
- W4385003673 hasRelatedWork W2356875448 @default.
- W4385003673 hasRelatedWork W2961085424 @default.
- W4385003673 hasRelatedWork W3015547233 @default.
- W4385003673 hasRelatedWork W3185852197 @default.
- W4385003673 hasRelatedWork W4214784181 @default.
- W4385003673 hasRelatedWork W4287900189 @default.
- W4385003673 hasRelatedWork W4312095844 @default.
- W4385003673 hasRelatedWork W4382322290 @default.
- W4385003673 isParatext "false" @default.
- W4385003673 isRetracted "false" @default.
- W4385003673 workType "article" @default.