{"updated":"2025-01-19T18:03:37.212833+00:00","links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00210675","sets":["581:10433:10437"]},"path":["10437"],"owner":"44499","recid":"210675","title":["Hierarchical Latent Words Language Models for Automatic Speech Recognition"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-04-15"},"_buckets":{"deposit":"69f6f393-2501-426e-bd94-1b0b9ddab051"},"_deposit":{"id":"210675","pid":{"type":"depid","value":"210675","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Hierarchical Latent Words Language Models for Automatic Speech Recognition","author_link":["533974","533972","533978","533976","533973","533977","533975","533971"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Hierarchical Latent Words Language Models for Automatic Speech Recognition"},{"subitem_title":"Hierarchical Latent Words Language Models for Automatic Speech Recognition","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[一般論文] hierarchical latent words language models, automatic speech recognition, domain robust language modeling","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2021-04-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"NTT Media Intelligence Laboratories, NTT Corporation"},{"subitem_text_value":"NTT Media Intelligence Laboratories, NTT Corporation"},{"subitem_text_value":"NTT Media Intelligence Laboratories, NTT Corporation"},{"subitem_text_value":"NTT Media Intelligence Laboratories, NTT Corporation"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"NTT Media Intelligence Laboratories, NTT Corporation","subitem_text_language":"en"},{"subitem_text_value":"NTT Media Intelligence Laboratories, NTT Corporation","subitem_text_language":"en"},{"subitem_text_value":"NTT Media Intelligence Laboratories, NTT Corporation","subitem_text_language":"en"},{"subitem_text_value":"NTT Media Intelligence Laboratories, NTT Corporation","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/210675/files/IPSJ-JNL6204023.pdf","label":"IPSJ-JNL6204023.pdf"},"date":[{"dateType":"Available","dateValue":"2023-04-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6204023.pdf","filesize":[{"value":"812.4 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"1a5e55cb-44ff-442d-88fc-290ed876c27f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Ryo, Masumura"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Taichi, Asami"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takanobu, Oba"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Sumitaka, Sakauchi"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Ryo, Masumura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Taichi, Asami","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takanobu, Oba","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Sumitaka, Sakauchi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"This paper presents hierarchical latent words language models (h-LWLMs) for improving automatic speech recognition (ASR) performance in out-of-domain tasks. Language models called h-LWLM are an advanced form of LWLM that are one one hopeful approach to domain robust language modeling. The key strength of the LWLMs is having a latent word space that helps to efficiently capture linguistic phenomena not present in a training data set. However, standard LWLMs cannot consider that the function and meaning of words are essentially hierarchical. Therefore, h-LWLMs employ a multiple latent word space with hierarchical structure by estimating a latent word of a latent word recursively. The hierarchical latent word space helps us to flexibly calculate generative probability for unseen words. This paper provides a definition of h-LWLM as well as a training method. In addition, we present two implementation methods that enable us to introduce the h-LWLMs into ASR tasks. Our experiments on a perplexity evaluation and an ASR evaluation show the effectiveness of h-LWLMs in out-of-domain tasks.\n------------------------------\nThis is a preprint of an article intended for publication Journal of\nInformation Processing(JIP). This preprint should not be cited. This\narticle should be cited as: Journal of Information Processing Vol.29(2021) (online)\nDOI　http://dx.doi.org/10.2197/ipsjjip.29.360\n------------------------------","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper presents hierarchical latent words language models (h-LWLMs) for improving automatic speech recognition (ASR) performance in out-of-domain tasks. Language models called h-LWLM are an advanced form of LWLM that are one one hopeful approach to domain robust language modeling. The key strength of the LWLMs is having a latent word space that helps to efficiently capture linguistic phenomena not present in a training data set. However, standard LWLMs cannot consider that the function and meaning of words are essentially hierarchical. Therefore, h-LWLMs employ a multiple latent word space with hierarchical structure by estimating a latent word of a latent word recursively. The hierarchical latent word space helps us to flexibly calculate generative probability for unseen words. This paper provides a definition of h-LWLM as well as a training method. In addition, we present two implementation methods that enable us to introduce the h-LWLMs into ASR tasks. Our experiments on a perplexity evaluation and an ASR evaluation show the effectiveness of h-LWLMs in out-of-domain tasks.\n------------------------------\nThis is a preprint of an article intended for publication Journal of\nInformation Processing(JIP). This preprint should not be cited. This\narticle should be cited as: Journal of Information Processing Vol.29(2021) (online)\nDOI　http://dx.doi.org/10.2197/ipsjjip.29.360\n------------------------------","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicIssueDates":{"bibliographicIssueDate":"2021-04-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"4","bibliographicVolumeNumber":"62"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":210675,"created":"2025-01-19T01:11:52.847170+00:00"}