WEKO3
アイテム
AURORA-2J: An Evaluation Framework for Japanese Noisy Speech Recognition
http://hdl.handle.net/2237/15046
http://hdl.handle.net/2237/150461d6e7ba7-5d6a-42ca-89a0-a9cb0e3e41ef
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
425.pdf (1.8 MB)
|
|
| アイテムタイプ | 学術雑誌論文 / Journal Article(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2011-07-06 | |||||
| タイトル | ||||||
| タイトル | AURORA-2J: An Evaluation Framework for Japanese Noisy Speech Recognition | |||||
| 言語 | en | |||||
| 著者 |
NAKAMURA, Satoshi
× NAKAMURA, Satoshi× TAKEDA, Kazuya× YAMAMOTO, Kazumasa× YAMADA, Takeshi× KUROIWA, Shingo× KITAOKA, Norihide× NISHIURA, Takanobu× SASOU, Akira× MIZUMACHI, Mitsunori× MIYAJIMA, Chiyomi× FUJIMOTO, Masakiyo× ENDO, Toshiki |
|||||
| アクセス権 | ||||||
| アクセス権 | open access | |||||
| アクセス権URI | http://purl.org/coar/access_right/c_abf2 | |||||
| 権利 | ||||||
| 権利情報 | Copyright (C) 2005 IEICE | |||||
| 言語 | en | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | noisy speech recognition | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | evaluation platform | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | performance differences over speakers | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | evaluation categories | |||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | This paper introduces an evaluation framework for Japanese noisy speech recognition named AURORA-2J. Speech recognition systems must still be improved to be robust to noisy environments, but this improvement requires development of the standard evaluation corpus and assessment technologies. Recently, the Aurora 2, 3 and 4 corpora and their evaluation scenarios have had significant impact on noisy speech recognition research. The AURORA-2J is a Japanese connected digits corpus and its evaluation scripts are designed in the same way as Aurora 2 with the help of European Telecommunications Standards Institute (ETSI) AURORA group. This paper describes the data collection, baseline scripts, and its baseline performance. We also propose a new performance analysis method that considers differences in recognition performance among speakers. This method is based on the word accuracy per speaker, revealing the degree of the individual difference of the recognition performance. We also propose categorization of modifications, applied to the original HTK baseline system, which helps in comparing the systems and in recognizing technologies that improve the performance best within the same category. | |||||
| 言語 | en | |||||
| 出版者 | ||||||
| 出版者 | Institute of Electronics, Information and Communication Engineers | |||||
| 言語 | en | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 資源タイプ | ||||||
| 資源タイプresource | http://purl.org/coar/resource_type/c_6501 | |||||
| タイプ | journal article | |||||
| 出版タイプ | ||||||
| 出版タイプ | VoR | |||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
| 関連情報 | ||||||
| 関連タイプ | isVersionOf | |||||
| 識別子タイプ | URI | |||||
| 関連識別子 | http://www.ieice.org/jpn/trans_online/index.html | |||||
| ISSN | ||||||
| 収録物識別子タイプ | PISSN | |||||
| 収録物識別子 | 0916-8532 | |||||
| 書誌情報 |
en : IEICE transactions on information and systems 巻 E88-D, 号 3, p. 535-544, 発行日 2005-03-01 |
|||||
| 著者版フラグ | ||||||
| 値 | publisher | |||||
| URI | ||||||
| 識別子 | http://www.ieice.org/jpn/trans_online/index.html | |||||
| 識別子タイプ | URI | |||||
| URI | ||||||
| 識別子 | http://hdl.handle.net/2237/15046 | |||||
| 識別子タイプ | HDL | |||||
