ダウンロード数: 355
このアイテムのファイル:
ファイル | 記述 | サイズ | フォーマット | |
---|---|---|---|---|
s13634-015-0246-6.pdf | 2.11 MB | Adobe PDF | 見る/開く |
タイトル: | Reverberant speech recognition combining deep neural networks and deep autoencoders augmented with a phone-class feature |
著者: | Mimura, Masato Sakai, Shinsuke Kawahara, Tatsuya https://orcid.org/0000-0002-2686-2296 (unconfirmed) |
著者名の別形: | 三村, 正人 |
キーワード: | Reverberant speech recognition Deep Neural Networks (DNN) Deep Autoencoder (DAE) |
発行日: | 23-Jul-2015 |
出版者: | SpringerOpen |
誌名: | EURASIP Journal on Advances in Signal Processing |
巻: | 2015 |
号: | 1 |
論文番号: | 62 |
抄録: | We propose an approach to reverberant speech recognition adopting deep learning in the front-end as well as b a c k-e n d o f a r e v e r b e r a n t s p e e c h r e c o g n i t i o n s y s t e m, a n d a n o v e l m e t h o d t o i m p r o v e t h e d e r e v e r b e r a t i o n p e r f o r m a n c e of the front-end network using phone-class information. At the front-end, we adopt a deep autoencoder (DAE) for enhancing the speech feature parameters, and speech recognition is performed in the back-end using DNN-HMM acoustic models trained on multi-condition data. The system was evaluated through the ASR task in the Reverb Challenge 2014. The DNN-HMM system trained on the multi-condition training set achieved a conspicuously higher word accuracy compared to the MLLR-adapted GMM-HMM system trained on the same data. Furthermore, feature enhancement with the deep autoencoder contributed to the improvement of recognition accuracy especially in the more adverse conditions. While the mapping between reverberant and clean speech in DAE-based dereverberation is conventionally conducted only with the acoustic information, we presume the mapping is also dependent on the phone information. Therefore, we propose a new scheme (pDAE), which augments a phone-class feature to the standard acoustic features as input. Two types of the phone-class feature are investigated. One is the hard recognition result of monophones, and the other is a soft representation derived from the posterior outputs of monophone DNN. The augmented feature in either type results in a significant improvement (7–8 % relative) from the standard DAE. |
著作権等: | © 2015 Mimura et al. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
URI: | http://hdl.handle.net/2433/201887 |
DOI(出版社版): | 10.1186/s13634-015-0246-6 |
出現コレクション: | 学術雑誌掲載論文等 |
このリポジトリに保管されているアイテムはすべて著作権により保護されています。