skip to content
Novel Techniques for Dialectal Arabic Speech Recognition Preview this item
ClosePreview this item
Checking...

Novel Techniques for Dialectal Arabic Speech Recognition

Author: Mohamed Elmahdy; Rainer Gruhn; Wolfgang Minker
Publisher: Boston, MA : Springer US, 2012.
Edition/Format:   eBook : Document : English : 2012View all editions and formats
Summary:
Novel Techniques for Dialectal Arabic Speech describes approaches to improve automatic speech recognition for dialectal Arabic. Since speech resources for dialectal Arabic speech recognition are very sparse, the authors describe how existing Modern Standard Arabic (MSA) speech data can be applied to dialectal Arabic speech recognition, while assuming that MSA is always a second language for all Arabic speakers. In  Read more...
Rating:

(not yet rated) 0 with reviews - Be the first.

Subjects
More like this

 

Find a copy online

Find a copy in the library

&AllPage.SpinnerRetrieving; Finding libraries that hold this item...

Details

Genre/Form: Electronic books
Additional Physical Format: Printed edition:
Material Type: Document, Internet resource
Document Type: Internet Resource, Computer File
All Authors / Contributors: Mohamed Elmahdy; Rainer Gruhn; Wolfgang Minker
ISBN: 9781461419068 1461419069
OCLC Number: 783117122
Description: 1 online resource
Contents: Fundamentals --
Speech Corpora --
Phonemic Acoustic Modeling --
Graphemic Acoustic Modeling --
Phonetic Transcription Using the Arabic Chat Alphabet.
Responsibility: by Mohamed Elmahdy, Rainer Gruhn, Wolfgang Minker.

Abstract:

Novel Techniques for Dialectal Arabic Speech describes approaches to improve automatic speech recognition for dialectal Arabic. Since speech resources for dialectal Arabic speech recognition are very sparse, the authors describe how existing Modern Standard Arabic (MSA) speech data can be applied to dialectal Arabic speech recognition, while assuming that MSA is always a second language for all Arabic speakers. In this book, Egyptian Colloquial Arabic (ECA) has been chosen as a typical Arabic dialect. ECA is the first ranked Arabic dialect in terms of number of speakers, and a high quality ECA speech corpus with accurate phonetic transcription has been collected. MSA acoustic models were trained using news broadcast speech. In order to cross-lingually use MSA in dialectal Arabic speech recognition, the authors have normalized the phoneme sets for MSA and ECA. After this normalization, they have applied state-of-the-art acoustic model adaptation techniques like Maximum Likelihood Linear Regression (MLLR) and Maximum A-Posteriori (MAP) to adapt existing phonemic MSA acoustic models with a small amount of dialectal ECA speech data. Speech recognition results indicate a significant increase in recognition accuracy compared to a baseline model trained with only ECA data.

Reviews

User-contributed reviews
Retrieving GoodReads reviews...
Retrieving DOGObooks reviews...

Tags

Be the first.
Confirm this request

You may have already requested this item. Please select Ok if you would like to proceed with this request anyway.

Linked Data


Primary Entity

<http://www.worldcat.org/oclc/783117122> # Novel Techniques for Dialectal Arabic Speech Recognition
    a schema:Book, schema:MediaObject, schema:CreativeWork ;
   library:oclcnum "783117122" ;
   library:placeOfPublication <http://experiment.worldcat.org/entity/work/data/1080491104#Place/boston_ma> ; # Boston, MA
   library:placeOfPublication <http://id.loc.gov/vocabulary/countries/mau> ;
   schema:about <http://experiment.worldcat.org/entity/work/data/1080491104#Topic/signal_image_and_speech_processing> ; # Signal, Image and Speech Processing
   schema:about <http://experiment.worldcat.org/entity/work/data/1080491104#Topic/language_translation_and_linguistics> ; # Language Translation and Linguistics
   schema:about <http://id.worldcat.org/fast/1154842> ; # Translators (Computer programs)
   schema:about <http://id.loc.gov/authorities/subjects/sh85077224> ; # Computational linguistics
   schema:about <http://id.worldcat.org/fast/1145830> ; # Telecommunication
   schema:about <http://id.loc.gov/authorities/subjects/sh85133270> ; # Telecommunication
   schema:about <http://dewey.info/class/006.454/> ;
   schema:about <http://experiment.worldcat.org/entity/work/data/1080491104#Topic/communications_engineering_networks> ; # Communications Engineering, Networks
   schema:about <http://experiment.worldcat.org/entity/work/data/1080491104#Topic/arabic> ; # Arabic
   schema:about <http://id.worldcat.org/fast/910312> ; # Engineering
   schema:about <http://experiment.worldcat.org/entity/work/data/1080491104#Topic/arabic_languages> ; # Arabic languages
   schema:about <http://id.loc.gov/authorities/subjects/sh85043176> ; # Engineering
   schema:about <http://experiment.worldcat.org/entity/work/data/1080491104#Topic/computational_linguistics> ; # Computational Linguistics
   schema:about <http://id.worldcat.org/fast/871998> ; # Computational linguistics
   schema:bookEdition "2012." ;
   schema:bookFormat schema:EBook ;
   schema:contributor <http://viaf.org/viaf/81784719> ; # Rainer Gruhn
   schema:contributor <http://viaf.org/viaf/7549860> ; # Wolfgang Minker
   schema:creator <http://viaf.org/viaf/187261255> ; # Mohamed Elmahdy
   schema:datePublished "2012" ;
   schema:description "Fundamentals -- Speech Corpora -- Phonemic Acoustic Modeling -- Graphemic Acoustic Modeling -- Phonetic Transcription Using the Arabic Chat Alphabet."@en ;
   schema:description "Novel Techniques for Dialectal Arabic Speech describes approaches to improve automatic speech recognition for dialectal Arabic. Since speech resources for dialectal Arabic speech recognition are very sparse, the authors describe how existing Modern Standard Arabic (MSA) speech data can be applied to dialectal Arabic speech recognition, while assuming that MSA is always a second language for all Arabic speakers. In this book, Egyptian Colloquial Arabic (ECA) has been chosen as a typical Arabic dialect. ECA is the first ranked Arabic dialect in terms of number of speakers, and a high quality ECA speech corpus with accurate phonetic transcription has been collected. MSA acoustic models were trained using news broadcast speech. In order to cross-lingually use MSA in dialectal Arabic speech recognition, the authors have normalized the phoneme sets for MSA and ECA. After this normalization, they have applied state-of-the-art acoustic model adaptation techniques like Maximum Likelihood Linear Regression (MLLR) and Maximum A-Posteriori (MAP) to adapt existing phonemic MSA acoustic models with a small amount of dialectal ECA speech data. Speech recognition results indicate a significant increase in recognition accuracy compared to a baseline model trained with only ECA data."@en ;
   schema:exampleOfWork <http://worldcat.org/entity/work/id/1080491104> ;
   schema:genre "Electronic books"@en ;
   schema:inLanguage "en" ;
   schema:isSimilarTo <http://worldcat.org/entity/work/data/1080491104#CreativeWork/> ;
   schema:name "Novel Techniques for Dialectal Arabic Speech Recognition"@en ;
   schema:productID "783117122" ;
   schema:publication <http://www.worldcat.org/title/-/oclc/783117122#PublicationEvent/boston_ma_springer_us_2012> ;
   schema:publisher <http://experiment.worldcat.org/entity/work/data/1080491104#Agent/springer_us> ; # Springer US
   schema:url <http://dx.doi.org/10.1007/978-1-4614-1906-8> ;
   schema:url <http://public.eblib.com/choice/publicfullrecord.aspx?p=884331> ;
   schema:workExample <http://worldcat.org/isbn/9781461419068> ;
   schema:workExample <http://dx.doi.org/10.1007/978-1-4614-1906-8> ;
   wdrs:describedby <http://www.worldcat.org/title/-/oclc/783117122> ;
    .


Related Entities

<http://experiment.worldcat.org/entity/work/data/1080491104#Topic/communications_engineering_networks> # Communications Engineering, Networks
    a schema:Intangible ;
   schema:name "Communications Engineering, Networks"@en ;
    .

<http://experiment.worldcat.org/entity/work/data/1080491104#Topic/computational_linguistics> # Computational Linguistics
    a schema:Intangible ;
   schema:name "Computational Linguistics"@en ;
    .

<http://experiment.worldcat.org/entity/work/data/1080491104#Topic/language_translation_and_linguistics> # Language Translation and Linguistics
    a schema:Intangible ;
   schema:name "Language Translation and Linguistics"@en ;
    .

<http://experiment.worldcat.org/entity/work/data/1080491104#Topic/signal_image_and_speech_processing> # Signal, Image and Speech Processing
    a schema:Intangible ;
   schema:name "Signal, Image and Speech Processing"@en ;
    .

<http://id.loc.gov/authorities/subjects/sh85043176> # Engineering
    a schema:Intangible ;
   schema:name "Engineering"@en ;
    .

<http://id.loc.gov/authorities/subjects/sh85077224> # Computational linguistics
    a schema:Intangible ;
   schema:name "Computational linguistics"@en ;
    .

<http://id.loc.gov/authorities/subjects/sh85133270> # Telecommunication
    a schema:Intangible ;
   schema:name "Telecommunication"@en ;
    .

<http://id.worldcat.org/fast/1145830> # Telecommunication
    a schema:Intangible ;
   schema:name "Telecommunication"@en ;
    .

<http://id.worldcat.org/fast/1154842> # Translators (Computer programs)
    a schema:Intangible ;
   schema:name "Translators (Computer programs)"@en ;
    .

<http://id.worldcat.org/fast/871998> # Computational linguistics
    a schema:Intangible ;
   schema:name "Computational linguistics"@en ;
    .

<http://id.worldcat.org/fast/910312> # Engineering
    a schema:Intangible ;
   schema:name "Engineering"@en ;
    .

<http://viaf.org/viaf/187261255> # Mohamed Elmahdy
    a schema:Person ;
   schema:familyName "Elmahdy" ;
   schema:givenName "Mohamed" ;
   schema:name "Mohamed Elmahdy" ;
    .

<http://viaf.org/viaf/7549860> # Wolfgang Minker
    a schema:Person ;
   schema:familyName "Minker" ;
   schema:givenName "Wolfgang" ;
   schema:name "Wolfgang Minker" ;
    .

<http://viaf.org/viaf/81784719> # Rainer Gruhn
    a schema:Person ;
   schema:familyName "Gruhn" ;
   schema:givenName "Rainer" ;
   schema:name "Rainer Gruhn" ;
    .

<http://worldcat.org/entity/work/data/1080491104#CreativeWork/>
    a schema:CreativeWork ;
   schema:description "Printed edition:" ;
   schema:isSimilarTo <http://www.worldcat.org/oclc/783117122> ; # Novel Techniques for Dialectal Arabic Speech Recognition
    .

<http://worldcat.org/isbn/9781461419068>
    a schema:ProductModel ;
   schema:isbn "1461419069" ;
   schema:isbn "9781461419068" ;
    .


Content-negotiable representations

Close Window

Please sign in to WorldCat 

Don't have an account? You can easily create a free account.