FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3014677573> ?p ?o ?g. }

• W3014677573 abstract "The task of automatic language identification (LID) involving multiple dialects of the same language family in the presence of noise is a challenging problem. In these scenarios, the identity of the language/dialect may be reliably present only in parts of the temporal sequence of the speech signal. The conventional approaches to LID (and for speaker recognition) ignore the sequence information by extracting long-term statistical summary of the recording assuming an independence of the feature frames. In this paper, we propose a neural network framework utilizing short-sequence information in language recognition. In particular, a new model is proposed for incorporating relevance in language recognition, where parts of speech data are weighted more based on their relevance for the language recognition task. This relevance weighting is achieved using the bidirectional long short-term memory (BLSTM) network with attention modeling. We explore two approaches, the first approach uses segment level i-vector/x-vector representations that are aggregated in the neural model and the second approach where the acoustic features are directly modeled in an end-to-end neural model. Experiments are performed using the language recognition task in NIST LRE 2017 Challenge using clean, noisy and multi-speaker speech data as well as in the RATS language recognition corpus. In these experiments on noisy LRE tasks as well as the RATS dataset, the proposed approach yields significant improvements over the conventional i-vector/x-vector based language recognition approaches as well as with other previous models incorporating sequence information." @default.
• W3014677573 created "2020-04-10" @default.
• W3014677573 creator A5002536077 @default.
• W3014677573 creator A5011775237 @default.
• W3014677573 creator A5016956141 @default.
• W3014677573 date "2020-04-02" @default.
• W3014677573 modified "2023-09-27" @default.
• W3014677573 title "Towards Relevance and Sequence Modeling in Language Recognition" @default.
• W3014677573 cites W1491108479 @default.
• W3014677573 cites W1514535095 @default.
• W3014677573 cites W1524333225 @default.
• W3014677573 cites W1916834241 @default.
• W3014677573 cites W1924770834 @default.
• W3014677573 cites W2033436836 @default.
• W3014677573 cites W2039057510 @default.
• W3014677573 cites W2039420750 @default.
• W3014677573 cites W2041823554 @default.
• W3014677573 cites W2056119007 @default.
• W3014677573 cites W2064675550 @default.
• W3014677573 cites W2078169166 @default.
• W3014677573 cites W2095833672 @default.
• W3014677573 cites W2103621378 @default.
• W3014677573 cites W2104457544 @default.
• W3014677573 cites W2131774270 @default.
• W3014677573 cites W2136848157 @default.
• W3014677573 cites W2142730757 @default.
• W3014677573 cites W2147512149 @default.
• W3014677573 cites W2148986421 @default.
• W3014677573 cites W2150355110 @default.
• W3014677573 cites W2150769028 @default.
• W3014677573 cites W2172287020 @default.
• W3014677573 cites W2219249508 @default.
• W3014677573 cites W2271840356 @default.
• W3014677573 cites W2290689761 @default.
• W3014677573 cites W2293851464 @default.
• W3014677573 cites W2395750323 @default.
• W3014677573 cites W2397940721 @default.
• W3014677573 cites W2398527292 @default.
• W3014677573 cites W2408021097 @default.
• W3014677573 cites W2486686145 @default.
• W3014677573 cites W2493697199 @default.
• W3014677573 cites W2518527613 @default.
• W3014677573 cites W2766219058 @default.
• W3014677573 cites W2805662243 @default.
• W3014677573 cites W2807511004 @default.
• W3014677573 cites W2807627734 @default.
• W3014677573 cites W2887979278 @default.
• W3014677573 cites W2940073716 @default.
• W3014677573 cites W2950635152 @default.
• W3014677573 cites W2962826786 @default.
• W3014677573 cites W2964308564 @default.
• W3014677573 cites W2972808922 @default.
• W3014677573 cites W3008749227 @default.
• W3014677573 cites W854541894 @default.
• W3014677573 cites W1525783482 @default.
• W3014677573 cites W2916297645 @default.
• W3014677573 hasPublicationYear "2020" @default.
• W3014677573 type Work @default.
• W3014677573 sameAs 3014677573 @default.
• W3014677573 citedByCount "0" @default.
• W3014677573 crossrefType "posted-content" @default.
• W3014677573 hasAuthorship W3014677573A5002536077 @default.
• W3014677573 hasAuthorship W3014677573A5011775237 @default.
• W3014677573 hasAuthorship W3014677573A5016956141 @default.
• W3014677573 hasConcept C111219384 @default.
• W3014677573 hasConcept C126838900 @default.
• W3014677573 hasConcept C129792486 @default.
• W3014677573 hasConcept C133892786 @default.
• W3014677573 hasConcept C137293760 @default.
• W3014677573 hasConcept C138885662 @default.
• W3014677573 hasConcept C153180895 @default.
• W3014677573 hasConcept C154945302 @default.
• W3014677573 hasConcept C158154518 @default.
• W3014677573 hasConcept C162324750 @default.
• W3014677573 hasConcept C17744445 @default.
• W3014677573 hasConcept C183115368 @default.
• W3014677573 hasConcept C187736073 @default.
• W3014677573 hasConcept C195324797 @default.
• W3014677573 hasConcept C199539241 @default.
• W3014677573 hasConcept C204321447 @default.
• W3014677573 hasConcept C2776230583 @default.
• W3014677573 hasConcept C2776401178 @default.
• W3014677573 hasConcept C2778112365 @default.
• W3014677573 hasConcept C2780451532 @default.
• W3014677573 hasConcept C28490314 @default.
• W3014677573 hasConcept C41008148 @default.
• W3014677573 hasConcept C41895202 @default.
• W3014677573 hasConcept C50644808 @default.
• W3014677573 hasConcept C54355233 @default.
• W3014677573 hasConcept C71924100 @default.
• W3014677573 hasConcept C86803240 @default.
• W3014677573 hasConceptScore W3014677573C111219384 @default.
• W3014677573 hasConceptScore W3014677573C126838900 @default.
• W3014677573 hasConceptScore W3014677573C129792486 @default.
• W3014677573 hasConceptScore W3014677573C133892786 @default.
• W3014677573 hasConceptScore W3014677573C137293760 @default.
• W3014677573 hasConceptScore W3014677573C138885662 @default.
• W3014677573 hasConceptScore W3014677573C153180895 @default.
• W3014677573 hasConceptScore W3014677573C154945302 @default.
• W3014677573 hasConceptScore W3014677573C158154518 @default.

• next