Fast-LSTM acoustic model for distant speech recognition

Rezki Trianto, Tzu Chiang Tai, Jia Ching Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Consumer Electronics, ICCE 2018
EditorsSaraju P. Mohanty, Peter Corcoran, Hai Li, Anirban Sengupta, Jong-Hyouk Lee
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
ISBN (Electronic)9781538630259
DOIs
StatePublished - 26 Mar 2018
Event2018 IEEE International Conference on Consumer Electronics, ICCE 2018 - Las Vegas, United States
Duration: 12 Jan 201814 Jan 2018

Publication series

Name2018 IEEE International Conference on Consumer Electronics, ICCE 2018
Volume2018-January

Conference

Conference2018 IEEE International Conference on Consumer Electronics, ICCE 2018
Country/TerritoryUnited States
CityLas Vegas
Period12/01/1814/01/18

Keywords

  • long short-term memory
  • Speech recognition
  • time delay neural networks

Fingerprint

Dive into the research topics of 'Fast-LSTM acoustic model for distant speech recognition'. Together they form a unique fingerprint.

Cite this