[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-490695-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-490695-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","syllabication-for-afrikaans-speech-synthesis-paper","Syllabification for Afrikaans speech synthesis - Paper","","This paper presents the continued development of a pronunciation resource for Afrikaans speech synthesis by augmenting an existing pronunciation dictionary to add syllable boundaries and stress. It evaluates grapheme-to-phoneme conversion and syllabification approaches derived from the dictionary. Cross-validation experiments indicate that joint sequence models effectively model pronunciations including syllable boundaries. The work concludes with informal observations and demonstrations of integration into a typical text-to-speech system.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/syllabication-for-afrikaans-speech-synthesis-paper/490695/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/syllabication-for-afrikaans-speech-synthesis-paper/490695.png","ImageObject",300,407,{"name":42,"@type":43},"นรินทร์","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-09","2026-10-01",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the main goal of the paper?","Question",{"text":63,"@type":64},"To develop a pronunciation resource for Afrikaans speech synthesis by extending an existing pronunciation dictionary with syllable boundaries and stress.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How are syllable boundaries added to the dictionary?",{"text":68,"@type":64},"By applying a rule-based syllabification algorithm to decompounded entries and then manually correcting the results.",{"name":70,"@type":61,"acceptedAnswer":71},"What do cross-validation experiments suggest about modelling pronunciations?",{"text":72,"@type":64},"Joint sequence models are effective at directly modelling pronunciations that include syllable boundaries.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},490695,1790903194,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":102,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":144},2336475104957,"https://ap-avatar.wpscdn.com/avatar/22000c4c6bd8a5076e1?x-image-process=image/resize,m_fixed,w_180,h_180&k=1787554080175789136","Syllabification for Afrikaans speech synthesis  \nDaniel R. van Niekerk  \nMultilingual Speech Technologies, North-West University,  \nVanderbijlpark, South Africa.  \nEmail: [daniel.vanniekerk@nwu.ac.za](daniel.vanniekerk@nwu.ac.za)  \nAbstract—This paper describes the continuing development of a pronunciation resource for speech synthesis of Afrikaans by augmenting an existing pronunciation dictionary to include syllable boundaries and stress. Furthermore, different approaches for grapheme to phoneme conversion and syllabification derived from the dictionary are evaluated. Cross-validation experiments suggest that joint sequence models are effective at directly modelling pronunciations including syllable boundaries. Finally, some informal observations and demonstrations are presented regarding the integration of this work into a typical text-to-speech system.  \nIndex Terms—pronunciation dictionary, syllabification, Afrikaans, speech synthesis, text-to-speech  \nI. INTRODUCTION  \nRecent work on text-to-speech (TTS) synthesis has applied increasingly sophisticated statistical and machine learning techniques to extract and generate patterns from appropriate speech corpora, i.e. corpus-based acoustic modelling and speech generation [1], [2] . In principle, some of these techniques are flexible enough to perform acoustic modelling directly (to various degrees) from the natural language text, thereby potentially bypassing intermediate signal or linguistic representations [3], [4] . Some of the advantages of these approaches include avoiding uncertainties or errors in intermediate representations, the possibility of optimising larger parts of systems directly, and reducing the cost associated with the development of intermediate resources (such as pronunciation dictionaries) . In practice, however, acoustic modelling for TTS usually involves several components and representations of both the audio signal (such as spectral envelope, fundamental frequency and segment durations) and text (typically words, syllables and phones) . The above-mentioned machine learning techniques are then used to model and generate the signal components from the linguistically motivated features [5] . While complicating the task of system-wide performance optimisation, intermediate representations can make acoustic modelling more tractable and allow for more explicit control over these aspects.  \nThis paper describes ongoing work towards augmenting lexical pronunciation resources for TTS in Afrikaans. One part of such resources is the lexicon, which for the purpose of TTS applications should ideally contain the following information [6]:  \n1) Orthographies and their pronunciations.  \n2) Part of speech (POS) and relevant semantic information to be used for disambiguation of entries.  \nRelevant lexical pronunciations (1) may include phone sequences (segmental), syllable boundaries and syllable stress and/or tone (suprasegmental) . In addition to the lexicon, it is necessary to have an accurate method for predicting out-ofvocabulary (OOV) words, since general purpose TTS systems are not usually expected to be restricted to a closed set of words at run-time.  \nThe specific contributions of this work are:  \n1) A description of work on adapting the pre-existing Resources for Closely Related Languages Afrikaans Pronunciation Dictionary (RCRL APD) [7] for Afrikaans TTS, including the definition of a syllabification protocol and addition of manually verified syllable boundaries.  \n2) An evaluation of models derived from the dictionary to predict new pronunciations (phones and syllable boundaries) .  \n3) Informal observations and a demonstration of initial work of adding syllable stress information and integrating the updated resources into an Afrikaans TTS system.  \nThe above points are described in the next three sections respectively, followed by Section V where future work is proposed.  \nII. PRONUNCIATION DICTIONARY DEVELOPMENT  \nAs mentioned in the point (1) above, this wor","cbCaih1ObcXTvQ1S","https://ap.wps.com/l/cbCaih1ObcXTvQ1S","pdf",499022,"English","# Introduction\n# Pronunciation Dictionary Development\n## Phone specification and conventions","[{\"question\":\"What is the main goal of the paper?\",\"answer\":\"To develop a pronunciation resource for Afrikaans speech synthesis by extending an existing pronunciation dictionary with syllable boundaries and stress.\"},{\"question\":\"How are syllable boundaries added to the dictionary?\",\"answer\":\"By applying a rule-based syllabification algorithm to decompounded entries and then manually correcting the results.\"},{\"question\":\"What do cross-validation experiments suggest about modelling pronunciations?\",\"answer\":\"Joint sequence models are effective at directly modelling pronunciations that include syllable boundaries.\"}]","Syllabification for Afrikaans speech synthesis - Paper | PDF",1790841421,15]