Comparison of Methods for Topic Classification of Spoken Inquiries

• Item type: Journal(1)
• 公開日: 2013-02-15
• タイトル: Comparison of Methods for Topic Classification of Spoken Inquiries
• タイトル / 言語: en
• タイトル: Comparison of Methods for Topic Classification of Spoken Inquiries
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [特集：音声ドキュメント処理] topic classification, support vector machine, PrefixSpan boosting, maximum entropy, stacked generalization
• 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: Nara Institute of Science and Technology
• 著者所属: Nara Institute of Science and Technology
• 著者所属: The Institute of Statistical Mathematics
• 著者所属: Nara Institute of Science and Technology
• 著者所属: Nara Institute of Science and Technology
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology
• 著者所属(英): en
• 著者所属(英): The Institute of Statistical Mathematics
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology
• 著者所属(英): en
• 著者所属(英): Nara Institute of Science and Technology
• 著者名: Rafael, Torres; Hiromichi, Kawanami; Tomoko, Matsui; Hiroshi, Saruwatari; Kiyohiro, Shikano
• 著者名(英): Rafael, Torres; Hiromichi, Kawanami; Tomoko, Matsui; Hiroshi, Saruwatari; Kiyohiro, Shikano
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: In this work, we address the topic classification of spoken inquiries in Japanese that are received by a speech-oriented guidance system operating in a real environment. The classification of spoken inquiries is often hindered by automatic speech recognition (ASR) errors, the sparseness of features and the shortness of spontaneous speech utterances. Here, we compare the performances of a support vector machine (SVM) with a radial basis function (RBF) kernel, PrefixSpan boosting (pboost) and the maximum entropy (ME) method, which are supervised learning methods. We also combine their predictions using a stacked generalization (SG) scheme. We also perform an evaluation using words or characters as features for the classifiers. Using characters as features is possible in Japanese owing to the presence of kanji, ideograms originating from Chinese characters that represent not only sounds but also meanings. We performed analyses on the performance of the above methods and their combination in dealing with the indicated problems. Experimental results show an F-measure of 86.87% for the classification of ASR results from children's inquiries with an average performance improvement of 2.81% compared with the performance of individual classifiers, and an F-measure of 93.96% with an average improvement of 1.89% for adults' inquiries when using the SG scheme and character features.; ------------------------------; 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.21(2013) No.2 (online); DOI http://dx.doi.org/10.2197/ipsjjip.21.157; ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: In this work, we address the topic classification of spoken inquiries in Japanese that are received by a speech-oriented guidance system operating in a real environment. The classification of spoken inquiries is often hindered by automatic speech recognition (ASR) errors, the sparseness of features and the shortness of spontaneous speech utterances. Here, we compare the performances of a support vector machine (SVM) with a radial basis function (RBF) kernel, PrefixSpan boosting (pboost) and the maximum entropy (ME) method, which are supervised learning methods. We also combine their predictions using a stacked generalization (SG) scheme. We also perform an evaluation using words or characters as features for the classifiers. Using characters as features is possible in Japanese owing to the presence of kanji, ideograms originating from Chinese characters that represent not only sounds but also meanings. We performed analyses on the performance of the above methods and their combination in dealing with the indicated problems. Experimental results show an F-measure of 86.87% for the classification of ASR results from children's inquiries with an average performance improvement of 2.81% compared with the performance of individual classifiers, and an F-measure of 93.96% with an average improvement of 1.89% for adults' inquiries when using the SG scheme and character features.; ------------------------------; 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.21(2013) No.2 (online); DOI http://dx.doi.org/10.2197/ipsjjip.21.157; ------------------------------
• 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 54, 号 2, 発行日 2013-02-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7764