Matches in SemOpenAlex for { <https://semopenalex.org/work/W2565624985> ?p ?o ?g. }
- W2565624985 abstract "In order to address the commonly met issue of overfitting in speech recognition, this article investigates Multi-Task Learning, when the auxiliary task focuses on speaker classification. Overfitting occurs when the amount of training data is limited, leading to an over-sensible acoustic model. Multi-Task Learning is a method, among many other regularization methods, which decreases the overfitting impact by forcing the acoustic model to train jointly for multiple different, but related, tasks. In this paper, we consider speaker classification as an auxiliary task in order to improve the generalization abilities of the acoustic model, by training the model to recognize the speaker, or find the closest one inside the training set. We investigate this Multi-Task Learning setup on the TIMIT database, while the acoustic modeling is performed using a Recurrent Neural Network with Long Short-Term Memory cells." @default.
- W2565624985 created "2017-01-06" @default.
- W2565624985 creator A5040916551 @default.
- W2565624985 creator A5042439255 @default.
- W2565624985 creator A5083563222 @default.
- W2565624985 date "2016-08-01" @default.
- W2565624985 modified "2023-09-23" @default.
- W2565624985 title "Speaker-aware long short-term memory multi-task learning for speech recognition" @default.
- W2565624985 cites W129870797 @default.
- W2565624985 cites W1545083717 @default.
- W2565624985 cites W1565000507 @default.
- W2565624985 cites W1978660892 @default.
- W2565624985 cites W1995562189 @default.
- W2565624985 cites W2046056978 @default.
- W2565624985 cites W2094035326 @default.
- W2565624985 cites W2105948329 @default.
- W2565624985 cites W2115730999 @default.
- W2565624985 cites W2115856579 @default.
- W2565624985 cites W2117130368 @default.
- W2565624985 cites W2137630452 @default.
- W2565624985 cites W2155273149 @default.
- W2565624985 cites W2156297475 @default.
- W2565624985 cites W2160815625 @default.
- W2565624985 cites W2166113160 @default.
- W2565624985 cites W2292492052 @default.
- W2565624985 cites W2913340405 @default.
- W2565624985 cites W4254751698 @default.
- W2565624985 doi "https://doi.org/10.1109/eusipco.2016.7760581" @default.
- W2565624985 hasPublicationYear "2016" @default.
- W2565624985 type Work @default.
- W2565624985 sameAs 2565624985 @default.
- W2565624985 citedByCount "17" @default.
- W2565624985 countsByYear W25656249852016 @default.
- W2565624985 countsByYear W25656249852017 @default.
- W2565624985 countsByYear W25656249852018 @default.
- W2565624985 countsByYear W25656249852019 @default.
- W2565624985 countsByYear W25656249852020 @default.
- W2565624985 countsByYear W25656249852021 @default.
- W2565624985 countsByYear W25656249852022 @default.
- W2565624985 countsByYear W25656249852023 @default.
- W2565624985 crossrefType "proceedings-article" @default.
- W2565624985 hasAuthorship W2565624985A5040916551 @default.
- W2565624985 hasAuthorship W2565624985A5042439255 @default.
- W2565624985 hasAuthorship W2565624985A5083563222 @default.
- W2565624985 hasConcept C119857082 @default.
- W2565624985 hasConcept C134306372 @default.
- W2565624985 hasConcept C154945302 @default.
- W2565624985 hasConcept C155635449 @default.
- W2565624985 hasConcept C162324750 @default.
- W2565624985 hasConcept C177148314 @default.
- W2565624985 hasConcept C177264268 @default.
- W2565624985 hasConcept C187736073 @default.
- W2565624985 hasConcept C199360897 @default.
- W2565624985 hasConcept C22019652 @default.
- W2565624985 hasConcept C23224414 @default.
- W2565624985 hasConcept C2776135515 @default.
- W2565624985 hasConcept C2778724510 @default.
- W2565624985 hasConcept C2780451532 @default.
- W2565624985 hasConcept C28006648 @default.
- W2565624985 hasConcept C28490314 @default.
- W2565624985 hasConcept C33923547 @default.
- W2565624985 hasConcept C41008148 @default.
- W2565624985 hasConcept C50644808 @default.
- W2565624985 hasConcept C61328038 @default.
- W2565624985 hasConceptScore W2565624985C119857082 @default.
- W2565624985 hasConceptScore W2565624985C134306372 @default.
- W2565624985 hasConceptScore W2565624985C154945302 @default.
- W2565624985 hasConceptScore W2565624985C155635449 @default.
- W2565624985 hasConceptScore W2565624985C162324750 @default.
- W2565624985 hasConceptScore W2565624985C177148314 @default.
- W2565624985 hasConceptScore W2565624985C177264268 @default.
- W2565624985 hasConceptScore W2565624985C187736073 @default.
- W2565624985 hasConceptScore W2565624985C199360897 @default.
- W2565624985 hasConceptScore W2565624985C22019652 @default.
- W2565624985 hasConceptScore W2565624985C23224414 @default.
- W2565624985 hasConceptScore W2565624985C2776135515 @default.
- W2565624985 hasConceptScore W2565624985C2778724510 @default.
- W2565624985 hasConceptScore W2565624985C2780451532 @default.
- W2565624985 hasConceptScore W2565624985C28006648 @default.
- W2565624985 hasConceptScore W2565624985C28490314 @default.
- W2565624985 hasConceptScore W2565624985C33923547 @default.
- W2565624985 hasConceptScore W2565624985C41008148 @default.
- W2565624985 hasConceptScore W2565624985C50644808 @default.
- W2565624985 hasConceptScore W2565624985C61328038 @default.
- W2565624985 hasLocation W25656249851 @default.
- W2565624985 hasOpenAccess W2565624985 @default.
- W2565624985 hasPrimaryLocation W25656249851 @default.
- W2565624985 hasRelatedWork W1542012215 @default.
- W2565624985 hasRelatedWork W1562688281 @default.
- W2565624985 hasRelatedWork W202591681 @default.
- W2565624985 hasRelatedWork W2050397613 @default.
- W2565624985 hasRelatedWork W2054353061 @default.
- W2565624985 hasRelatedWork W2072788898 @default.
- W2565624985 hasRelatedWork W2346074333 @default.
- W2565624985 hasRelatedWork W2382278371 @default.
- W2565624985 hasRelatedWork W2565624985 @default.
- W2565624985 hasRelatedWork W2072450853 @default.
- W2565624985 isParatext "false" @default.
- W2565624985 isRetracted "false" @default.
- W2565624985 magId "2565624985" @default.