[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-227530-en":3,"doc-seo-227530-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},227530,137451211410,"\tCallum ","https://ap-avatar.wpscdn.com/avatar/2000bb0a9246f588df?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786362646172706240",8,"Research & Report","Towards a Unified ASR System for the Armenian Standards - Workshop Proceedings","Armenian is an under-resourced language with growing interest in digital tools, particularly Automatic Speech Recognition (ASR). The paper addresses the technical implications of Armenian’s two standard variants, Eastern Armenian and Western Armenian, which differ across phonetic and phonological levels. It reviews available data resources, outlines the processing challenges created by variant divergence, and proposes a forward methodology aimed at a unified ASR system.","Proceedings of the Workshop on Processing Language Variation: Digital Armenian (DigitAm 2022) @LREC2022 , pages 38–42 Marseille, 20 June 2022  \n© European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0  \nTowards a Unified ASR System for the Armenian Standards  \nSamuel Chakmakjian1,2 , Ilaine Wang2  \n1 SeDyL (CNRS-Inalco), 2ERTIM (Inalco)  \n7 rue Guy Môquet 94800 Villejuif, 2 rue de Lille 75007 Paris {samuel.chakmakjian, [ilaine.wang}@inalco.fr](ilaine.wang}@inalco.fr)  \nAbstract  \nArmenian is a traditionally under-resourced language, which has seen a recent uptick in interest in the development of its tools and presence in the digital domain. Some of this recent interest has centred around the development of Automatic Speech Recognition (ASR) technologies. However, the language boasts two standard variants which diverge on multiple typological and structural levels. In this work, we examine some of the available bodies of data for ASR construction, present the challenges in the processing of these data and propose a methodology going forward.  \nKeywords: speech corpus, ASR, forced alignment  \n1. The Problem  \nArmenian is a traditionally under-resourced language, which has seen a recent uptick in interest in the development of its tools and presence in the digital domain.  \nSome of this recent interest has centred around the development of Automatic Speech Recognition (ASR) technologies. However, the language boasts two standard variants which diverge on multiple typological and structural levels.  \n1.1. A Tale of Two Phonologies  \nThis structural divide is the most salient at a phoneticphonological level, with Standard Eastern Armenian’s (SEA) phonemic inventory containing 36 phonemes (30 consonants, 6 vowels), and Standard Western Armenian’s (SWA) inventory being comprised of 30 phonemes (24 consonants, 6 vowels) .  \nThe vocalic systems of SEA and SWA are largely the similar, with the five cardinal vowels /i, e, a, o, u/ anda mid-central vowel /@/ . The consonant systems share the same nasals, fricatives, and approximants (/m, n, f, v, s, z, S, Z, X, K, h, j, l/) . SEA distinguishes between two rhotics, a tap /R/ and a trill /r/, whereas SWA does not make such a distinction. The most problematic feature of the divergence in phonologies however, is that of the plosive and affricate series in SWA and SEA. SEA’s plosive and affricate phonemes have a three-way voicing distinction: voiced, voiceless, and voiceless aspirated. Modern SWA has a two-way voicing system of voiced and voiceless aspirated. The plosive and affricates phonemes of SEA are therefore the following: /b, p, ph , d, t, th , g, k, kh , dz, ts, tsh , dZ, tS, tSh/, and the plosive and affricate phonemes of SWAare as follows: /b, ph , d, th , g, kh , dz, tsh , dZ, tSh/ .  \nTable 1 provides an example of the diverging phonetic realisations of three similar items.  \n\n| Item | SEA | SWA | Translation |\n| --- | --- | --- | --- |\n| 〈 ba􀀜 〉 | [bAr] | [ phAR] | ’word’ |\n| 〈 par 〉 | [pAR] | [bAR] | ’dance’ |\n| 〈 􀀞a􀀜 〉 | [phAr] | [phAR] | ’placenta’ |\n\nTable 1: Three words and their pronunciations in SEA vs. SWA  \n1.2. Towards a Multivariant Culture  \nDespite this divergence in phonemic inventories, many factors render a unified system preferable. The two variants share a writing system and base lexicon, and while the two variants may be clearly distinct from one another, their speech communities are not. Amongst proficient speakers, there is a high level of mutual intelligibility. Furthurmore, the social realities of increased contact between speakers of SEA (traditionally found in the Republic of Armenia, Iran and countries of the post-Soviet zone) and speakers of SWA (traditionally found in post-Ottoman diasporan communities founded in the Middle East, Europe and the Americas) manifest in multivariant households, and sometimes multivariant speakers.  \nAn increasing presence of SEA speakers in traditionally SWA-speaking diasporan communities, and an incr","cbCaimnpnjWRH5uz","https://ap.wps.com/l/cbCaimnpnjWRH5uz","pdf",203651,1,5,"English","en",105,"# Abstract\n# The Problem\n## A Tale of Two Phonologies\n## Towards a Multivariant Culture","[{\"question\":\"Why is building a unified ASR system for Armenian challenging?\",\"answer\":\"Armenian has two standard variants that diverge on multiple typological and structural levels, creating difficulties in processing speech and mapping inputs to the correct graphemes and pronunciations.\"},{\"question\":\"What phonological differences are discussed between Eastern and Western Armenian?\",\"answer\":\"The paper contrasts the phoneme inventories, including distinctions in rhotics and a three-way voicing system in Eastern Armenian versus a two-way system in Western Armenian for plosives and affricates.\"},{\"question\":\"What methodology does the paper propose to move toward unifying ASR?\",\"answer\":\"It suggests combining approaches such as Grapheme-to-Phoneme (G2P) modeling with strategies inspired by discriminating between similar languages, using variant identification to handle Armenian’s multivariant nature.\"}]","Towards a Unified ASR System for the Armenian Standards - Workshop Proceedings | PDF",1789009737,13,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"towards-a-unified-asr-system-for-the-armenian-standards-workshop-proceedings","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/towards-a-unified-asr-system-for-the-armenian-standards-workshop-proceedings/227530/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-09-11","2026-09-10",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is building a unified ASR system for Armenian challenging?","Question",{"text":76,"@type":77},"Armenian has two standard variants that diverge on multiple typological and structural levels, creating difficulties in processing speech and mapping inputs to the correct graphemes and pronunciations.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What phonological differences are discussed between Eastern and Western Armenian?",{"text":81,"@type":77},"The paper contrasts the phoneme inventories, including distinctions in rhotics and a three-way voicing system in Eastern Armenian versus a two-way system in Western Armenian for plosives and affricates.",{"name":83,"@type":74,"acceptedAnswer":84},"What methodology does the paper propose to move toward unifying ASR?",{"text":85,"@type":77},"It suggests combining approaches such as Grapheme-to-Phoneme (G2P) modeling with strategies inspired by discriminating between similar languages, using variant identification to handle Armenian’s multivariant nature.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":21,"slug":138},19,"General","general"]