@techreport{oai:ipsj.ixsq.nii.ac.jp:00056936,
 author = {秋田, 祐哉 and 河原, 達也 and Yuya, AKITA and TatsuyaKAWAHARA},
 issue = {127(2005-SLP-059)},
 month = {Dec},
 note = {講演や会議のような話し言葉の音声認識では，言語モデルの学習に際してタスクにマッチしたデータ，すなわち忠実な書き起こしテキストの量が限られていることが問題となっている．本稿では，大規模な文書データベースに基づく言語モデルの統計量から，話し言葉言語モデルの統計量を推定する変換手法を提案する．提案する統計的変換モデルでは，話し言葉に特徴的な言語表現がモデル化され，それらの変換確率も推定される・変換の発生する文脈パターンと確率は，音声の忠実な書き起こしとそれを文書スタイルに整形したテキストからなる小規模パラレルコーパスを用いて学習される．変換の適用範囲を広げ，信頼性を高めるために，単語を文脈としたモデルから品詞を文脈としたモデルにバックオフする枠組みを導入する．提案法を国会音声の認識タスクに適用したところ，テストセットパープレキシティを大きく改善することができた．, One of the most significant problems in language modeling of spontaneous speech such as meetings and lectures is that only limited amount of matched training data, i.e. faithful transcript for the relevant task domain, is available. In this paper, we propose a novel transformation approach to estimate language model statistics of spontaneous speech from a document-style text database, which is often available with a large scale. The proposed statistical transformation model is designed for modeling characteristic linguistic phenomena in spontaneous speech and estimating their occurrence probabilities. These contextual patterns and probabilities are derived from a small amount of parallel aligned corpus of the faithful transcripts and their document-style texts. To realize wide coverage and reliable estimation, a model based on part-of-speech (POS) is also prepared to provide a back-off scheme from a word-based model. The approach has been successfully applied to estimation of the language model for National Congress meetings from their minute archives, and significant reduction of test-set perplexity is achieved.},
 title = {統計的機械翻訳の枠組みに基づく言語モデルの話し言葉スタイルへの変換},
 year = {2005}
}