@techreport{oai:ipsj.ixsq.nii.ac.jp:00102195,
 author = {Sheng, Li and Yuya, Akita and Tatsuya, Kawahara and Sheng, Li and Yuya, Akita and Tatsuya, Kawahara},
 issue = {4},
 month = {Jul},
 note = {The paper addresses a scheme of lightly-supervised training of acoustic model, which exploits a large amount of data with closed caption texts but not faithful transcripts. In the proposed scheme, a sequence of the closed caption text and the ASR hypothesis by the baseline system are aligned. Then, a dedicated classifier is designed and trained to select the correct one among them or reject both. It is demonstrated that the classifier can effectively filter the usable data for acoustic model training. The scheme realizes automatic training of the model with an increased amount of data. A significant improvement in the ASR accuracy is achieved from the baseline system and also in comparison with the conventional method of lightly-supervised training based on simple matching or confidence measure score., The paper addresses a scheme of lightly-supervised training of acoustic model, which exploits a large amount of data with closed caption texts but not faithful transcripts. In the proposed scheme, a sequence of the closed caption text and the ASR hypothesis by the baseline system are aligned. Then, a dedicated classifier is designed and trained to select the correct one among them or reject both. It is demonstrated that the classifier can effectively filter the usable data for acoustic model training. The scheme realizes automatic training of the model with an increased amount of data. A significant improvement in the ASR accuracy is achieved from the baseline system and also in comparison with the conventional method of lightly-supervised training based on simple matching or confidence measure score.},
 title = {Classifier-based Data Selection for Lightly-Supervised Training of Acoustic Model for Lecture Transcription},
 year = {2014}
}