Fast-LSTM acoustic model for distant speech recognition

Rezki Trianto, Tzu Chiang Tai, Jia Ching Wang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

11 引文 斯高帕斯(Scopus)

摘要

The distant-talking automatic speech recognition (ASR) currently becomes an important task in a speech recognition area. Traditionally, hybrid Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) approach are used for ASR. This paper will discuss some deep neural network (DNN) techniques for acoustic modeling, as well as lattice rescoring techniques for ASR. The proposed Fast-long short-term memory neural network (Fast-LSTM) acoustic model combines the time delay neural network (TDNN) and LSTM network to reduce the training time of the standard LSTM acoustic model.

原文???core.languages.en_GB???
主出版物標題2018 IEEE International Conference on Consumer Electronics, ICCE 2018
編輯Saraju P. Mohanty, Peter Corcoran, Hai Li, Anirban Sengupta, Jong-Hyouk Lee
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1-4
頁數4
ISBN(電子)9781538630259
DOIs
出版狀態已出版 - 26 3月 2018
事件2018 IEEE International Conference on Consumer Electronics, ICCE 2018 - Las Vegas, United States
持續時間: 12 1月 201814 1月 2018

出版系列

名字2018 IEEE International Conference on Consumer Electronics, ICCE 2018
2018-January

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2018 IEEE International Conference on Consumer Electronics, ICCE 2018
國家/地區United States
城市Las Vegas
期間12/01/1814/01/18

指紋

深入研究「Fast-LSTM acoustic model for distant speech recognition」主題。共同形成了獨特的指紋。

引用此