Art

J-GLOBAL ID：202002244249095296   Reference number：20A0560004

Robust Multichannel End-to-End Speech Recognition Based on Multi-Output Densenet

多出力Densenetに基づくロバスト多チャンネルエンドツーエンド音声認識

Author (2)： ZHENG Chonghui (Tokyo Inst. of Technol., Tokyo, JPN) ,  SHINOZAKI Takahiro (Tokyo Inst. of Technol., Tokyo, JPN)
Material： 情報処理学会研究報告(Web)  (IPSJ Technical Report (Web))
Volume： 2020  Issue： SLP-131  Page： Vol.2020-SLP-131,No.10,1-3 (WEB ONLY)  Publication year： Feb. 06, 2020 
JST Material Number： U0451A  Document type： Proceedings
Article type： 短報  Country of issue： Japan (JPN)  Language： ENGLISH (EN)

Thesaurus term： *channel ,  *end-to-end signaling system ,  *speech recognition ,  *communication system ,  *neural network (biomodel) ,  *adaptive training ,  *Learning ,  beam forming ,  model ,  error rate ,  *robust speech recognition ,  *discipline ,  *Multiple-Input Multiple-Output ,  *education and training
Semi thesaurus term： Long short term memory ,  *end to end ,  *training ,  acoustic model ,  *multichannel ,  *Multiple-Input Multiple-Output

JST classification (2)： Pattern recognition  (JE07000S) ,  Artificial intelligence  (JE08000Z)

Reference (10)：

• Erdogan, Hakan, et al. ”Improved mvdr beamforming using single-channel mask prediction networks.” Interspeech. 2016.
• Heymann, Jahn, Lukas Drude, and Reinhold Haeb-Umbach. ”Neural network based spectral mask estimation for acoustic beamforming.”2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2016.
• Pfeifenberger, Lukas, Matthias Zöhrer, and Franz Pernkopf. ”DNN-based speech mask estimation for eigenvector beamforming.” 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2017.
• Ochiai, Tsubasa, et al. ”Unified architecture for multichannel end-to-end speech recognition with neural beamforming.” IEEE Journal of Selected Topics in Signal Processing 11.8 (2017): 1274-1288.
• Xiao, Xiong, et al. ”On time-frequency mask estimation for MVDR beamforming with application in robust speech recognition.” 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2017.

Terms in the title (4)： ロバスト ,  多チャンネル ,  エンドツーエンド ,  音声認識