Hierarchical Latent Words Language Models for Automatic Speech Recognition

• Item type: Journal(1)
• 公開日: 2021-04-15
• タイトル: Hierarchical Latent Words Language Models for Automatic Speech Recognition
• タイトル / 言語: en
• タイトル: Hierarchical Latent Words Language Models for Automatic Speech Recognition
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [一般論文] hierarchical latent words language models, automatic speech recognition, domain robust language modeling
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: NTT Media Intelligence Laboratories, NTT Corporation
• 著者所属: NTT Media Intelligence Laboratories, NTT Corporation
• 著者所属: NTT Media Intelligence Laboratories, NTT Corporation
• 著者所属: NTT Media Intelligence Laboratories, NTT Corporation
• 著者所属(英): en
• 著者所属(英): NTT Media Intelligence Laboratories, NTT Corporation
• 著者所属(英): en
• 著者所属(英): NTT Media Intelligence Laboratories, NTT Corporation
• 著者所属(英): en
• 著者所属(英): NTT Media Intelligence Laboratories, NTT Corporation
• 著者所属(英): en
• 著者所属(英): NTT Media Intelligence Laboratories, NTT Corporation
• 著者名: Ryo, Masumura; Taichi, Asami; Takanobu, Oba; Sumitaka, Sakauchi
• 著者名(英): Ryo, Masumura; Taichi, Asami; Takanobu, Oba; Sumitaka, Sakauchi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: 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.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.29(2021) (online); DOI http://dx.doi.org/10.2197/ipsjjip.29.360; ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: 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.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.29(2021) (online); DOI http://dx.doi.org/10.2197/ipsjjip.29.360; ------------------------------
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN00116647
• 書誌情報: 情報処理学会論文誌; 巻 62, 号 4, 発行日 2021-04-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7764