Classifier-based Data Selection for Lightly-Supervised Training of Acoustic Model for Lecture Transcription
スポンサーリンク
概要
- 論文の詳細を見る
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.
- 2014-07-17
著者
-
Tatsuya Kawahara
Kyoto University
-
Tatsuya Kawahara
School Of Informatics Kyoto University
-
Sheng Li
School of Informatics, Kyoto University
-
Yuya Akita
School of Informatics, Kyoto University
関連論文
- Construction of a Test Collection for Spoken Document Retrieval from Lecture Audio Data
- Joint Phrase Alignment and Extraction for Statistical Machine Translation
- Comparison of Discriminative Models for Lexicon Optimization for ASR of Agglutinative Language
- Partial and Synchronized Caption Generation to Enhance the Listening Comprehension Skills of Second Language Learners
- Partial and Synchronized Caption Generation to Enhance the Listening Comprehension Skills of Second Language Learners
- Classifier-based Data Selection for Lightly-Supervised Training of Acoustic Model for Lecture Transcription
- Identification of Oxide Phases in Oxide Dispersion Strengthened PM2000 Steel