Art

J-GLOBAL ID：201502253975601492   Reference number：15A0216193

Deep Neural Networkに基づく日本語音声認識の基礎評価

Author (3)： KANDA NAOYUKI (日立 中研) ,  TAKEDA RYU (日立 中研) ,  OBUCHI YASUNARI (日立 中研)
Material： 情報処理学会研究報告(Web)  (IPSJ Technical Report (Web))
Volume： 2013  Issue： SLP-97  Page： WEB ONLY VOL.2013-SLP-97,NO.8  Publication year： Jul. 18, 2013 
JST Material Number： U0451A  Document type： Proceedings
Article type： 原著論文  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： *speech recognition ,  *neural network (biomodel) ,  Japanese ,  task performance ,  Machine Learning ,  evaluation test ,  spoken language ,  *corpus ,  model ,  error rate ,  phoneme (morpheme) ,  accuracy ,  deep structure (semantics)
Semi thesaurus term： acoustic model ,  Recognition Accuracy

JST classification (3)： Pattern recognition  (JE07000S) ,  Neurocomputers  (JC06010Q) ,  Information processing in general  (AC05010A)

Reference (23)：

• Seide, F., Li, G. and Yu, D.: Conversational speech transcription using context-dependent deep neural networks, In Proc. Interspeech, pp. 437-440 (2011).
• Graves, A., rahman Mohamed, A. and Hinton, G.: Speech Recognition with Deep Recurrent Neural Networks, In Proc. ICASSP, IEEE, pp. 6645-6649 (2013).
• Deng, L., Abdel-Hamid, O. and Yu, D.: A Deep Convolutional Neural Network using Heterogeneous Pooling for Trading Acoustic Invariance with Phonetic Confusion, In Proc. ICASSP, IEEE, pp. 6669-6673 (2013).
• Seide, F., Li, G., Chen, X. and Yu, D.: Feature engineering in context-dependent deep neural networks for conversational speech transcription, In Proc. ASRU, IEEE, pp. 24-29 (2011).
• Seltzer, M., Yu, D. and Wang, Y.: An Investigation of Deep Neural Networks for Noise Robust Speech Recognition, In Proc. ICASSP, IEEE, pp. 7398-7402 (2013).

Terms in the title (4)： 日本語 ,  音声認識 ,  基礎 ,  評価