Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292092154> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4292092154 abstract "Most state-of-the-art speech systems are using Deep Neural Networks (DNNs). Those systems require a large amount of data to be learned. Hence, learning state-of-the-art frameworks on under-resourced speech languages/problems is a difficult task. Problems could be the limited amount of data for impaired speech. Furthermore, acquiring more data and/or expertise is time-consuming and expensive. In this paper we position ourselves for the following speech processing tasks: Automatic Speech Recognition, speaker identification and emotion recognition. To assess the problem of limited data, we firstly investigate state-of-the-art Automatic Speech Recognition systems as it represents the hardest tasks (due to the large variability in each language). Next, we provide an overview of techniques and tasks requiring fewer data. In the last section we investigate few-shot techniques as we interpret under-resourced speech as a few-shot problem. In that sense we propose an overview of few-shot techniques and perspectives of using such techniques for the focused speech problems in this survey. It occurs that the reviewed techniques are not well adapted for large datasets. Nevertheless, some promising results from the literature encourage the usage of such techniques for speech processing." @default.
- W4292092154 created "2022-08-17" @default.
- W4292092154 creator A5013101884 @default.
- W4292092154 creator A5018248112 @default.
- W4292092154 creator A5020176155 @default.
- W4292092154 date "2020-03-09" @default.
- W4292092154 modified "2023-09-29" @default.
- W4292092154 title "Deep Neural Networks for Automatic Speech Processing: A Survey from Large Corpora to Limited Data" @default.
- W4292092154 doi "https://doi.org/10.48550/arxiv.2003.04241" @default.
- W4292092154 hasPublicationYear "2020" @default.
- W4292092154 type Work @default.
- W4292092154 citedByCount "0" @default.
- W4292092154 crossrefType "posted-content" @default.
- W4292092154 hasAuthorship W4292092154A5013101884 @default.
- W4292092154 hasAuthorship W4292092154A5018248112 @default.
- W4292092154 hasAuthorship W4292092154A5020176155 @default.
- W4292092154 hasBestOaLocation W42920921541 @default.
- W4292092154 hasConcept C108583219 @default.
- W4292092154 hasConcept C11413529 @default.
- W4292092154 hasConcept C116834253 @default.
- W4292092154 hasConcept C154945302 @default.
- W4292092154 hasConcept C162324750 @default.
- W4292092154 hasConcept C187736073 @default.
- W4292092154 hasConcept C204321447 @default.
- W4292092154 hasConcept C2780451532 @default.
- W4292092154 hasConcept C28490314 @default.
- W4292092154 hasConcept C2984842247 @default.
- W4292092154 hasConcept C41008148 @default.
- W4292092154 hasConcept C48103436 @default.
- W4292092154 hasConcept C50644808 @default.
- W4292092154 hasConcept C59822182 @default.
- W4292092154 hasConcept C61328038 @default.
- W4292092154 hasConcept C86803240 @default.
- W4292092154 hasConceptScore W4292092154C108583219 @default.
- W4292092154 hasConceptScore W4292092154C11413529 @default.
- W4292092154 hasConceptScore W4292092154C116834253 @default.
- W4292092154 hasConceptScore W4292092154C154945302 @default.
- W4292092154 hasConceptScore W4292092154C162324750 @default.
- W4292092154 hasConceptScore W4292092154C187736073 @default.
- W4292092154 hasConceptScore W4292092154C204321447 @default.
- W4292092154 hasConceptScore W4292092154C2780451532 @default.
- W4292092154 hasConceptScore W4292092154C28490314 @default.
- W4292092154 hasConceptScore W4292092154C2984842247 @default.
- W4292092154 hasConceptScore W4292092154C41008148 @default.
- W4292092154 hasConceptScore W4292092154C48103436 @default.
- W4292092154 hasConceptScore W4292092154C50644808 @default.
- W4292092154 hasConceptScore W4292092154C59822182 @default.
- W4292092154 hasConceptScore W4292092154C61328038 @default.
- W4292092154 hasConceptScore W4292092154C86803240 @default.
- W4292092154 hasLocation W42920921541 @default.
- W4292092154 hasOpenAccess W4292092154 @default.
- W4292092154 hasPrimaryLocation W42920921541 @default.
- W4292092154 hasRelatedWork W2081647779 @default.
- W4292092154 hasRelatedWork W2281534628 @default.
- W4292092154 hasRelatedWork W2604802223 @default.
- W4292092154 hasRelatedWork W2896257747 @default.
- W4292092154 hasRelatedWork W2920938200 @default.
- W4292092154 hasRelatedWork W2963218179 @default.
- W4292092154 hasRelatedWork W2984883371 @default.
- W4292092154 hasRelatedWork W3082779874 @default.
- W4292092154 hasRelatedWork W3107474891 @default.
- W4292092154 hasRelatedWork W4225605131 @default.
- W4292092154 isParatext "false" @default.
- W4292092154 isRetracted "false" @default.
- W4292092154 workType "article" @default.