FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1571506536> ?p ?o ?g. }

• W1571506536 endingPage "1724" @default.
• W1571506536 startingPage "1721" @default.
• W1571506536 abstract "In this paper, we analyze the impact of five Arabic dialects on the front-end and pronunciation dictionary components of an Automatic Speech Recognition (ASR) system. We use ASR's phonetic decision tree as a diagnostic tool to compare the robustness of MFCC and MLP front-ends to dialectal variations in the speech data and found that MLP Bottle-Neck features are less robust to such variations. We also perform a rule-based analysis of the pronunciation dictionary, which enables us to identify dialectal words in the vocabulary and automatically generate pronunciations for unseen words. We show that our technique produces pronunciations with an average phone error rate 9.2%. Arabic language is characterized by its multitude of dialects. Although Modern Standard Arabic (MSA) is used in writing, TV/radio broadcasts and for formal communication, all informal communication is typically carried out in one of the regional dialects of Arabic. Dialectal variations influence the pronunciation dictionary, acoustic and language models in an ASR. Previous works on dialectal Arabic ASR include cross- dialectal data sharing (1), improved pronunciation and language modeling (2, 3), etc. In this paper, we describe our experiments on a dialectal Arabic speech database, where we focus on analyzing the behavior of different front-ends and pronunciation dictionary due to dialectal variations between speakers. We evaluate Mel-Frequency Cepstral Coefficients (MFCC) and Multi-Layer Perceptrons (MLP), on their ability to handle these variations that arise due to different dialects. Extending our previous work on gender normalization (4), we use phonetic decision trees as a diagnostic tool to analyze the influence of dialect in the clustered models. We introduce questions pertaining to dialect in addition to context in the building of the decision tree. We then build the tree to cluster the contexts and calculate the number of leaves that belong to branches with dialectal questions. The ratio of such 'dialectal' models to the total model size is used as a measure for dialect normalization. The higher the ratio, the more models are affected by the dialect, hence less normalization and vice versa. We further extend our analysis to the pronunciation dictionary, where we investigate ways to generate rule-based pronunciations for unseen words in a dialect with minimum manual effort. Our setup features a 'Pan-Arabic' dictionary, which contains pronunciations typically found in five Arabic dialects. We analyze the pronunciation variants in our common dictionary using acoustic model alignments to derive the dialect-specific pronunciations for each word. This forms the source of our rule-learning algorithm which maps word pronunciations from one dialect to another. These rules are then used to generate pronunciations for unseen words and the accuracy is estimated." @default.
• W1571506536 created "2016-06-24" @default.
• W1571506536 creator A5010424125 @default.
• W1571506536 creator A5012623245 @default.
• W1571506536 creator A5039261815 @default.
• W1571506536 creator A5058049725 @default.
• W1571506536 creator A5083764317 @default.
• W1571506536 creator A5085262529 @default.
• W1571506536 date "2011-08-01" @default.
• W1571506536 modified "2023-09-22" @default.
• W1571506536 title "Analysis of Dialectal Influence in Pan-Arabic ASR" @default.
• W1571506536 cites W1520177497 @default.
• W1571506536 cites W1564887926 @default.
• W1571506536 cites W1583428434 @default.
• W1571506536 cites W162588823 @default.
• W1571506536 cites W1644467064 @default.
• W1571506536 cites W1779680350 @default.
• W1571506536 cites W2009639677 @default.
• W1571506536 cites W2024903555 @default.
• W1571506536 cites W2124420443 @default.
• W1571506536 cites W2124973918 @default.
• W1571506536 cites W2159948109 @default.
• W1571506536 cites W2165712214 @default.
• W1571506536 cites W2171074980 @default.
• W1571506536 doi "https://doi.org/10.1184/r1/6473042.v1" @default.
• W1571506536 hasPublicationYear "2011" @default.
• W1571506536 type Work @default.
• W1571506536 sameAs 1571506536 @default.
• W1571506536 citedByCount "1" @default.
• W1571506536 countsByYear W15715065362012 @default.
• W1571506536 crossrefType "proceedings-article" @default.
• W1571506536 hasAuthorship W1571506536A5010424125 @default.
• W1571506536 hasAuthorship W1571506536A5012623245 @default.
• W1571506536 hasAuthorship W1571506536A5039261815 @default.
• W1571506536 hasAuthorship W1571506536A5058049725 @default.
• W1571506536 hasAuthorship W1571506536A5083764317 @default.
• W1571506536 hasAuthorship W1571506536A5085262529 @default.
• W1571506536 hasConcept C138885662 @default.
• W1571506536 hasConcept C154945302 @default.
• W1571506536 hasConcept C204321447 @default.
• W1571506536 hasConcept C2777601683 @default.
• W1571506536 hasConcept C2778243841 @default.
• W1571506536 hasConcept C2780844864 @default.
• W1571506536 hasConcept C28490314 @default.
• W1571506536 hasConcept C40969351 @default.
• W1571506536 hasConcept C41008148 @default.
• W1571506536 hasConcept C41895202 @default.
• W1571506536 hasConcept C96455323 @default.
• W1571506536 hasConceptScore W1571506536C138885662 @default.
• W1571506536 hasConceptScore W1571506536C154945302 @default.
• W1571506536 hasConceptScore W1571506536C204321447 @default.
• W1571506536 hasConceptScore W1571506536C2777601683 @default.
• W1571506536 hasConceptScore W1571506536C2778243841 @default.
• W1571506536 hasConceptScore W1571506536C2780844864 @default.
• W1571506536 hasConceptScore W1571506536C28490314 @default.
• W1571506536 hasConceptScore W1571506536C40969351 @default.
• W1571506536 hasConceptScore W1571506536C41008148 @default.
• W1571506536 hasConceptScore W1571506536C41895202 @default.
• W1571506536 hasConceptScore W1571506536C96455323 @default.
• W1571506536 hasLocation W15715065361 @default.
• W1571506536 hasOpenAccess W1571506536 @default.
• W1571506536 hasPrimaryLocation W15715065361 @default.
• W1571506536 hasRelatedWork W143242639 @default.
• W1571506536 hasRelatedWork W1998245987 @default.
• W1571506536 hasRelatedWork W2073211979 @default.
• W1571506536 hasRelatedWork W2076960297 @default.
• W1571506536 hasRelatedWork W2109288487 @default.
• W1571506536 hasRelatedWork W2117160306 @default.
• W1571506536 hasRelatedWork W2129887376 @default.
• W1571506536 hasRelatedWork W2157075408 @default.
• W1571506536 hasRelatedWork W2170681008 @default.
• W1571506536 hasRelatedWork W2259875887 @default.
• W1571506536 hasRelatedWork W2296039906 @default.
• W1571506536 hasRelatedWork W2296417358 @default.
• W1571506536 hasRelatedWork W2307960051 @default.
• W1571506536 hasRelatedWork W2806800387 @default.
• W1571506536 hasRelatedWork W2893600191 @default.
• W1571506536 hasRelatedWork W2911976377 @default.
• W1571506536 hasRelatedWork W2967913065 @default.
• W1571506536 hasRelatedWork W3092459676 @default.
• W1571506536 hasRelatedWork W3155483372 @default.
• W1571506536 hasRelatedWork W2160660158 @default.
• W1571506536 isParatext "false" @default.
• W1571506536 isRetracted "false" @default.
• W1571506536 magId "1571506536" @default.
• W1571506536 workType "article" @default.