FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2557978073> ?p ?o ?g. }

• W2557978073 abstract "Recent studies have shown that in the case of under-resourced languages, use of articulatory features (AF) emerging from an articulatory model results in improved automatic speech recognition (ASR) compared to conventional mel frequency cepstral coefficient (MFCC) features. Articulatory features are more robust to noise and pronunciation variability compared to conventional acoustic features. To extract articulatory features, one method is to take conventional acoustic features like MFCC and build an articulatory classifier that would output articulatory features (known as pseudo-AF). However, these classifiers require a mapping from phone to different articulatory labels (AL) (e.g., place of articulation and manner of articulation), which is not readily available for many of the under-resourced languages. In this article, we have proposed an automated technique to generate phone-to-articulatory label (phone-to-AL) mapping for a new target language based on the knowledge of phone-to-AL mapping of a well-resourced language. The proposed mapping technique is based on the center-phone capturing property of interpolation vectors emerging from the recently proposed phone cluster adaptive training (Phone-CAT) method. Phone-CAT is an acoustic modeling technique that belongs to the broad category of canonical state models (CSM) that includes subspace Gaussian mixture model (SGMM). In Phone-CAT, the interpolation vector belonging to a particular context-dependent state has maximum weight for the center-phone in case of monophone clusters or by the AL of the center-phone in case of AL clusters. These relationships from the various context-dependent states are used to generate a phone-to-AL mapping. The Phone-CAT technique makes use of all the speech data belonging to a particular context-dependent state. Therefore, multiple segments of speech are used to generate the mapping, which makes it more robust to noise and other variations. In this study, we have obtained a phone-to-AL mapping for three under-resourced Indian languages namely Assamese, Hindi and Tamil based on the phone-to-AL mapping available for English. With the generated mappings, articulatory features are extracted for these languages using varying amounts of data in order to build an articulatory classifier. Experiments were also performed in a cross-lingual scenario assuming a small training data set (ź 2źh) from each of the Indian languages with articulatory classifiers built using a lot of training data (ź 22źh) from other languages including English (Switchboard task). Interestingly, cross-lingual performance is comparable to that of an articulatory classifier built with large amounts of native training data. Using articulatory features, more than 30% relative improvement was observed over the conventional MFCC features for all the three languages in a DNN framework." @default.
• W2557978073 created "2016-12-08" @default.
• W2557978073 creator A5005220677 @default.
• W2557978073 creator A5085660348 @default.
• W2557978073 date "2017-02-01" @default.
• W2557978073 modified "2023-09-26" @default.
• W2557978073 title "An automated technique to generate phone-to-articulatory label mapping" @default.
• W2557978073 cites W116245344 @default.
• W2557978073 cites W1484387534 @default.
• W2557978073 cites W1487082501 @default.
• W2557978073 cites W1524333225 @default.
• W2557978073 cites W1549576988 @default.
• W2557978073 cites W1974098377 @default.
• W2557978073 cites W1981706894 @default.
• W2557978073 cites W1986174057 @default.
• W2557978073 cites W1987538184 @default.
• W2557978073 cites W2018375232 @default.
• W2557978073 cites W2021775343 @default.
• W2557978073 cites W2039763773 @default.
• W2557978073 cites W2052382192 @default.
• W2557978073 cites W2069631319 @default.
• W2557978073 cites W2079508481 @default.
• W2557978073 cites W2080400971 @default.
• W2557978073 cites W2101392473 @default.
• W2557978073 cites W2106392848 @default.
• W2557978073 cites W2108586753 @default.
• W2557978073 cites W2120137673 @default.
• W2557978073 cites W2127982613 @default.
• W2557978073 cites W2143493821 @default.
• W2557978073 cites W2153189098 @default.
• W2557978073 cites W2159731626 @default.
• W2557978073 cites W2160815625 @default.
• W2557978073 cites W2407897255 @default.
• W2557978073 cites W44815768 @default.
• W2557978073 doi "https://doi.org/10.1016/j.specom.2016.11.010" @default.
• W2557978073 hasPublicationYear "2017" @default.
• W2557978073 type Work @default.
• W2557978073 sameAs 2557978073 @default.
• W2557978073 citedByCount "7" @default.
• W2557978073 countsByYear W25579780732017 @default.
• W2557978073 countsByYear W25579780732018 @default.
• W2557978073 countsByYear W25579780732019 @default.
• W2557978073 countsByYear W25579780732020 @default.
• W2557978073 countsByYear W25579780732022 @default.
• W2557978073 crossrefType "journal-article" @default.
• W2557978073 hasAuthorship W2557978073A5005220677 @default.
• W2557978073 hasAuthorship W2557978073A5085660348 @default.
• W2557978073 hasConcept C138885662 @default.
• W2557978073 hasConcept C151730666 @default.
• W2557978073 hasConcept C151989614 @default.
• W2557978073 hasConcept C153180895 @default.
• W2557978073 hasConcept C154945302 @default.
• W2557978073 hasConcept C23224414 @default.
• W2557978073 hasConcept C2777421447 @default.
• W2557978073 hasConcept C2778707766 @default.
• W2557978073 hasConcept C2779343474 @default.
• W2557978073 hasConcept C28490314 @default.
• W2557978073 hasConcept C32834561 @default.
• W2557978073 hasConcept C41008148 @default.
• W2557978073 hasConcept C41895202 @default.
• W2557978073 hasConcept C52622490 @default.
• W2557978073 hasConcept C61224824 @default.
• W2557978073 hasConcept C76155785 @default.
• W2557978073 hasConcept C86803240 @default.
• W2557978073 hasConcept C95623464 @default.
• W2557978073 hasConceptScore W2557978073C138885662 @default.
• W2557978073 hasConceptScore W2557978073C151730666 @default.
• W2557978073 hasConceptScore W2557978073C151989614 @default.
• W2557978073 hasConceptScore W2557978073C153180895 @default.
• W2557978073 hasConceptScore W2557978073C154945302 @default.
• W2557978073 hasConceptScore W2557978073C23224414 @default.
• W2557978073 hasConceptScore W2557978073C2777421447 @default.
• W2557978073 hasConceptScore W2557978073C2778707766 @default.
• W2557978073 hasConceptScore W2557978073C2779343474 @default.
• W2557978073 hasConceptScore W2557978073C28490314 @default.
• W2557978073 hasConceptScore W2557978073C32834561 @default.
• W2557978073 hasConceptScore W2557978073C41008148 @default.
• W2557978073 hasConceptScore W2557978073C41895202 @default.
• W2557978073 hasConceptScore W2557978073C52622490 @default.
• W2557978073 hasConceptScore W2557978073C61224824 @default.
• W2557978073 hasConceptScore W2557978073C76155785 @default.
• W2557978073 hasConceptScore W2557978073C86803240 @default.
• W2557978073 hasConceptScore W2557978073C95623464 @default.
• W2557978073 hasLocation W25579780731 @default.
• W2557978073 hasOpenAccess W2557978073 @default.
• W2557978073 hasPrimaryLocation W25579780731 @default.
• W2557978073 hasRelatedWork W1490506669 @default.
• W2557978073 hasRelatedWork W1513984940 @default.
• W2557978073 hasRelatedWork W1543083551 @default.
• W2557978073 hasRelatedWork W1967687764 @default.
• W2557978073 hasRelatedWork W1995312914 @default.
• W2557978073 hasRelatedWork W2080758042 @default.
• W2557978073 hasRelatedWork W2091650508 @default.
• W2557978073 hasRelatedWork W2105948329 @default.
• W2557978073 hasRelatedWork W2116173893 @default.
• W2557978073 hasRelatedWork W2130392381 @default.
• W2557978073 hasRelatedWork W2131405704 @default.
• W2557978073 hasRelatedWork W2143355529 @default.
• W2557978073 hasRelatedWork W2154162514 @default.
• W2557978073 hasRelatedWork W2160978380 @default.

• next