Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366321231> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4366321231 endingPage "164" @default.
- W4366321231 startingPage "146" @default.
- W4366321231 abstract "Current trends in NLP emphasize universal models and learning from pre-trained models. This article explores these trends and advanced models of pre-service learning. Inputs are converted into words or contextual embeddings that serve as inputs to encoders and decoders. The corpus of the author's publications over the past six years is used as the object of the research. The main methods of research are the analysis of scientific literature, prototyping, and experimental use of systems in the direction of research. Speech recognition players are divided into players with huge computing resources for whom training on large unlabeled data is a common procedure and players who are focused on training small local speech recognition models on pre-labeled audio data due to a lack of resources. Approaches and frameworks for working with unlabeled data and limited computing resources are almost not present, and methods based on iterative training are not developed and require scientific efforts for development. The research aims to develop methods of iterative training on unlabeled audio data to obtain productively ready speech recognition models with greater accuracy and limited resources. A separate block proposes methods of data preparation for use in training speech recognition systems and a pipeline for automatic training of speech recognition systems using pseudo marking of audio data. The prototype and solution of a real business problem of emotion detection demonstrate the capabilities and limitations of owl recognition systems and emotional states. With the use of the proposed methods of pseudo-labeling, it is possible to obtain recognition accuracy close to the market leaders without significant investment in computing resources, and for languages with a small amount of open data, it can even be surpassed." @default.
- W4366321231 created "2023-04-20" @default.
- W4366321231 creator A5028892313 @default.
- W4366321231 date "2023-01-01" @default.
- W4366321231 modified "2023-10-18" @default.
- W4366321231 title "COMPLEX METHOD FOR AUTOMATIC RECOGNITION OF NATURAL LANGUAGE AND EMOTIONAL STATE" @default.
- W4366321231 cites W1498436455 @default.
- W4366321231 cites W2033256038 @default.
- W4366321231 cites W2064675550 @default.
- W4366321231 cites W2127141656 @default.
- W4366321231 cites W2138368989 @default.
- W4366321231 cites W2327501763 @default.
- W4366321231 cites W2345144146 @default.
- W4366321231 cites W2346704485 @default.
- W4366321231 cites W2803193013 @default.
- W4366321231 cites W2962739339 @default.
- W4366321231 cites W2964110616 @default.
- W4366321231 cites W2964199361 @default.
- W4366321231 cites W2964539095 @default.
- W4366321231 cites W2972440193 @default.
- W4366321231 cites W2972778435 @default.
- W4366321231 cites W3017312369 @default.
- W4366321231 cites W3024869864 @default.
- W4366321231 cites W3028860956 @default.
- W4366321231 cites W3048407879 @default.
- W4366321231 cites W3103005696 @default.
- W4366321231 cites W3134880260 @default.
- W4366321231 cites W3178085672 @default.
- W4366321231 cites W3185921853 @default.
- W4366321231 cites W3193433576 @default.
- W4366321231 cites W3202481517 @default.
- W4366321231 cites W3212880672 @default.
- W4366321231 cites W4226165131 @default.
- W4366321231 doi "https://doi.org/10.28925/2663-4023.2023.19.146164" @default.
- W4366321231 hasPublicationYear "2023" @default.
- W4366321231 type Work @default.
- W4366321231 citedByCount "0" @default.
- W4366321231 crossrefType "journal-article" @default.
- W4366321231 hasAuthorship W4366321231A5028892313 @default.
- W4366321231 hasBestOaLocation W43663212311 @default.
- W4366321231 hasConcept C119857082 @default.
- W4366321231 hasConcept C154945302 @default.
- W4366321231 hasConcept C155635449 @default.
- W4366321231 hasConcept C157968479 @default.
- W4366321231 hasConcept C199360897 @default.
- W4366321231 hasConcept C204321447 @default.
- W4366321231 hasConcept C2524010 @default.
- W4366321231 hasConcept C2777210771 @default.
- W4366321231 hasConcept C28490314 @default.
- W4366321231 hasConcept C33923547 @default.
- W4366321231 hasConcept C41008148 @default.
- W4366321231 hasConcept C43521106 @default.
- W4366321231 hasConcept C61328038 @default.
- W4366321231 hasConceptScore W4366321231C119857082 @default.
- W4366321231 hasConceptScore W4366321231C154945302 @default.
- W4366321231 hasConceptScore W4366321231C155635449 @default.
- W4366321231 hasConceptScore W4366321231C157968479 @default.
- W4366321231 hasConceptScore W4366321231C199360897 @default.
- W4366321231 hasConceptScore W4366321231C204321447 @default.
- W4366321231 hasConceptScore W4366321231C2524010 @default.
- W4366321231 hasConceptScore W4366321231C2777210771 @default.
- W4366321231 hasConceptScore W4366321231C28490314 @default.
- W4366321231 hasConceptScore W4366321231C33923547 @default.
- W4366321231 hasConceptScore W4366321231C41008148 @default.
- W4366321231 hasConceptScore W4366321231C43521106 @default.
- W4366321231 hasConceptScore W4366321231C61328038 @default.
- W4366321231 hasIssue "19" @default.
- W4366321231 hasLocation W43663212311 @default.
- W4366321231 hasOpenAccess W4366321231 @default.
- W4366321231 hasPrimaryLocation W43663212311 @default.
- W4366321231 hasRelatedWork W2020540721 @default.
- W4366321231 hasRelatedWork W2106992993 @default.
- W4366321231 hasRelatedWork W2121486117 @default.
- W4366321231 hasRelatedWork W2157598242 @default.
- W4366321231 hasRelatedWork W22517275 @default.
- W4366321231 hasRelatedWork W2368779261 @default.
- W4366321231 hasRelatedWork W2374918184 @default.
- W4366321231 hasRelatedWork W2619911963 @default.
- W4366321231 hasRelatedWork W2620660273 @default.
- W4366321231 hasRelatedWork W3107474891 @default.
- W4366321231 hasVolume "3" @default.
- W4366321231 isParatext "false" @default.
- W4366321231 isRetracted "false" @default.
- W4366321231 workType "article" @default.