FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W331796780> ?p ?o ?g. }

• W331796780 abstract "This paper presents a novel approach to acoustic model adaptation of a recognizer for non-native spontaneous speech in the context of recognizing candidates’ responses in a test of spoken English. Instead of collecting and then transcribing spontaneous speech data, a read speech corpus is created where non-native speakers of English read English sentences of different degrees of pronunciation difficulty with respect to their native language. The motivation for this approach is (1) to save time and cost associated with transcribing spontaneous speech, and (2) to allow for a targeted training of the recognizer, focusing particularly on those phoneme environments which are difficult to pronounce correctly by non-native speakers and hence have a higher likelihood of being misrecognized. As a criterion for selecting the sentences to be read, we develop a novel score, the “phonetic challenge score”, consisting of a measure for native language-specific difficulties described in the second-language acquisition literature and also of a statistical measure based on the cross-entropy between phoneme sequences of the native language and English. We collected about 23,000 read sentences from 200 speakers in four language groups: Chinese, Japanese, Korean, and Spanish. We used this data for acoustic model adaptation of a spontaneous speech recognizer and compared recognition performance between the unadapted baseline and the system after adaptation on a held-out set from the English test responses data set. The results show that using this targeted read speech material for acoustic model adaptation does reduce the word error rate significantly for two of four language groups of the spontaneous speech test set, while changes of the two other language groups are not significant. Insdex Terms: acoustic model adaptation, non-native spontaneous speech, cross-lingual phonetic difficulty" @default.
• W331796780 created "2016-06-24" @default.
• W331796780 creator A5025218028 @default.
• W331796780 creator A5029161525 @default.
• W331796780 creator A5035313772 @default.
• W331796780 creator A5051420882 @default.
• W331796780 creator A5058023327 @default.
• W331796780 creator A5069537054 @default.
• W331796780 date "2009-09-06" @default.
• W331796780 modified "2023-09-29" @default.
• W331796780 title "Adapting the acoustic model of a speech recognizer for varied proficiency non-native spontaneous speech using read speech with language-specific pronunciation difficulty" @default.
• W331796780 cites W1556910286 @default.
• W331796780 cites W1978986151 @default.
• W331796780 cites W2024088004 @default.
• W331796780 cites W2032117164 @default.
• W331796780 cites W2066086299 @default.
• W331796780 cites W2119864770 @default.
• W331796780 cites W2293503202 @default.
• W331796780 doi "https://doi.org/10.21437/interspeech.2009-217" @default.
• W331796780 hasPublicationYear "2009" @default.
• W331796780 type Work @default.
• W331796780 sameAs 331796780 @default.
• W331796780 citedByCount "1" @default.
• W331796780 crossrefType "proceedings-article" @default.
• W331796780 hasAuthorship W331796780A5025218028 @default.
• W331796780 hasAuthorship W331796780A5029161525 @default.
• W331796780 hasAuthorship W331796780A5035313772 @default.
• W331796780 hasAuthorship W331796780A5051420882 @default.
• W331796780 hasAuthorship W331796780A5058023327 @default.
• W331796780 hasAuthorship W331796780A5069537054 @default.
• W331796780 hasConcept C138885662 @default.
• W331796780 hasConcept C14999030 @default.
• W331796780 hasConcept C155635449 @default.
• W331796780 hasConcept C204321447 @default.
• W331796780 hasConcept C2780844864 @default.
• W331796780 hasConcept C28490314 @default.
• W331796780 hasConcept C41008148 @default.
• W331796780 hasConcept C41895202 @default.
• W331796780 hasConcept C61328038 @default.
• W331796780 hasConcept C73411735 @default.
• W331796780 hasConcept C91863865 @default.
• W331796780 hasConceptScore W331796780C138885662 @default.
• W331796780 hasConceptScore W331796780C14999030 @default.
• W331796780 hasConceptScore W331796780C155635449 @default.
• W331796780 hasConceptScore W331796780C204321447 @default.
• W331796780 hasConceptScore W331796780C2780844864 @default.
• W331796780 hasConceptScore W331796780C28490314 @default.
• W331796780 hasConceptScore W331796780C41008148 @default.
• W331796780 hasConceptScore W331796780C41895202 @default.
• W331796780 hasConceptScore W331796780C61328038 @default.
• W331796780 hasConceptScore W331796780C73411735 @default.
• W331796780 hasConceptScore W331796780C91863865 @default.
• W331796780 hasLocation W3317967801 @default.
• W331796780 hasOpenAccess W331796780 @default.
• W331796780 hasPrimaryLocation W3317967801 @default.
• W331796780 hasRelatedWork W2012847626 @default.
• W331796780 hasRelatedWork W2060471688 @default.
• W331796780 hasRelatedWork W2127646729 @default.
• W331796780 hasRelatedWork W2291624303 @default.
• W331796780 hasRelatedWork W2548001695 @default.
• W331796780 hasRelatedWork W3166169565 @default.
• W331796780 hasRelatedWork W3188693104 @default.
• W331796780 hasRelatedWork W4281389974 @default.
• W331796780 hasRelatedWork W47429295 @default.
• W331796780 hasRelatedWork W2181951031 @default.
• W331796780 isParatext "false" @default.
• W331796780 isRetracted "false" @default.
• W331796780 magId "331796780" @default.
• W331796780 workType "article" @default.