| アイテムタイプ |
文献 / Documents(1) |
| 公開日 |
2017-08-29 |
| アクセス権 |
|
|
アクセス権 |
open access |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_6501 |
|
資源タイプ |
journal article |
| 出版社版DOI |
|
|
|
関連識別子 |
http://search.ieice.org/bin/summary.php?id=e99-d_10_2444&category=D&year=2016&lang=E&abst= |
| 出版タイプ |
|
|
出版タイプ |
VoR |
|
出版タイプResource |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| タイトル |
|
|
タイトル |
Investigation of DNN-Based Audio-Visual Speech Recognition (Special Section on Recent Advances in Machine Learning for Spoken Language Processing) |
| 著者 |
タムラ, サトシ
ニノミヤ, ヒロシ
北岡, 教英
オオスガ, シン
イリベ, ユリエ
タケダ, カズヤ
ハヤミズ, サトル
|
| 抄録 |
|
|
内容記述 |
Audio-Visual Speech Recognition (AVSR) is one of techniques to enhance robustness of speech recognizer in noisy or real environments. On the other hand, Deep Neural Networks (DNNs) have recently attracted a lot of attentions of researchers in the speech recognition field, because we can drastically improve recognition performance by using DNNs. There are two ways to employ DNN techniques for speech recognition: a hybrid approach and a tandem approach; in the hybrid approach an emission probability on each Hidden Markov Model (HMM) state is computed using a DNN, while in the tandem approach a DNN is composed into a feature extraction scheme. In this paper, we investigate and compare several DNN-based AVSR methods to mainly clarify how we should incorporate audio and visual modalities using DNNs. We carried out recognition experiments using a corpus CENSREC-1-AV, and we discuss the results to find out the best DNN-based AVSR modeling. Then it turns out that a tandem-based method using audio Deep Bottle-Neck Features (DBNFs) and visual ones with multi-stream HMMs is the most suitable, followed by a hybrid approach and another tandem scheme using audio-visual DBNFs. |
| キーワード |
|
|
主題 |
audio-visual speech recognition |
| キーワード |
|
|
主題 |
deep neural network |
| キーワード |
|
|
主題 |
Deep Bottleneck Feature |
| キーワード |
|
|
主題 |
multi-stream HMM |
| 書誌情報 |
en : IEICE Transactions on Information and Systems
巻 E99-D,
号 10,
p. 2444-2451,
発行日 2016-10-01
|
| 収録物ID |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
17451361 |
| 収録物ID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AA11510321 |
| 出版者 |
|
|
出版者 |
The Institute of Electronics, Information and Communication Engineers |
| 備考 |
|
|
値 |
IEICE Transactions Online TOP：http://search.ieice.org/ |
| 権利情報 |
|
|
権利情報 |
(c)2016 The Institute of Electronics, Information and Communication Engineers |
| EID |
|
|
識別子 |
315662 |
| 言語 |
|
|
言語 |
eng |
ieice_trans_e99-d_10_2444.pdf (808 KB)
