{"doi":"10.1109/icsda.2016.7919010","title":"Unsupervised graphoneme alignment evaluation for grapheme-to-phoneme conversion on complex asian-language orthographies","abstract":null,"journal":"2016 Conference of The Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA)","year":2016,"id":620989,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1603296,"name":"Sumonmas Thatphithakkul","orcid":null,"position":1,"is_corresponding":false},{"id":1603295,"name":"Chatchawarn Hansakunbuntheung","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Unsupervised graphoneme alignment evaluation for grapheme-to-phoneme conversion on complex asian-language orthographies","abstract":"Grapheme-to-Phoneme conversion (G2P) is a key component in text-to-speech and speech-to-text applications. Developing G2P for a new language needs grapheme-phoneme aligned data that is a time-consumed task. Previous works introduced graphoneme, m-to-n grapheme-phoneme sequence pair, as an alignment unit that can be applied to unsupervised alignment approach. Due to complex grapheme-phoneme alignment in Asian languages; for instance, inter-syllabic and intra-syllabic grapheme-phoneme cross-alignment and implicit tone assignment from orthographies, conventional contiguous character-based graphonemes might not be applicable. Thus, this paper investigates G2P performances using unsupervised graphoneme-based alignment techniques with varied lengths of graphonemes across Asian languages. We vary the lengths of graphonemes ranging from character level to supra-syllable level. To evaluate the G2P performance over Asian languages, we apply the alignments on four Asian grapheme-phoneme dictionaries including Mongolian, Lao, Thai and Myanmar. The evaluations of the unsupervised graphoneme-based alignments across the Asian languages yield high word accuracies of 79.18%, 81.63%, 91.28% and 95.13% for G2P applications in Myanmar, Thai, Lao and Mongolian, respectively.","is_dataset_classified":null,"base_score":0.0,"endowment":0.0,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"19767382","pmcid":null,"openalex_id":"https://openalex.org/W2610662399","authors":[],"funders":[],"total_grants":0,"fwci":0.0,"citation_percentile":0.19084733,"influential_citations":0,"citation_trend":[],"oa_status":"closed","license":null,"oa_locations":[{"url":"http://xplorestaging.ieee.org/ielx7/7911896/7918968/07919010.pdf?arnumber=7919010","host_type":"publisher"},{"url":"https://doi.org/10.1109/icsda.2016.7919010","host_type":""}],"fields_of_study":["Natural Language Processing Techniques","Topic Modeling","Text Readability and Simplification"],"mesh_terms":[],"keywords":["Grapheme","Syllable","Computer science","Syllabic verse","Character (mathematics)","Natural language processing","Artificial intelligence","Word (group theory)","Speech recognition","Linguistics","Mathematics"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Quality Education"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-03T12:50:42.926338Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}