HOME > Detail View

Detail View

음성 인식을 위한 다중 심층 신경망 병렬 학습

음성 인식을 위한 다중 심층 신경망 병렬 학습

Material type
학위논문
Personal Author
이은상 李殷相
Title Statement
음성 인식을 위한 다중 심층 신경망 병렬 학습 = Parallel training for deep neural network based speech recognizers / 李殷相
Publication, Distribution, etc
서울 :   고려대학교 대학원,   2017  
Physical Medium
vi, 52장 : 도표 ; 26 cm
기타형태 저록
parallel training for deep neural network based speech recognizers   (DCOLL211009)000000076704  
학위논문주기
학위논문(석사)-- 고려대학교 대학원, 컴퓨터·전파통신공학과, 2017. 8
학과코드
0510   6D36   1066  
General Note
지도교수: 陸東錫  
부록: A. 최적의 epoch 설정  
Bibliography, Etc. Note
참고문헌: 장 49-52
이용가능한 다른형태자료
PDF 파일로도 이용가능;   Requires PDF file reader(application/pdf)  
비통제주제어
deep learning, parallel training, speech recognition, deep neural network,,
000 00000nam c2200205 c 4500
001 000045915426
005 20230712105214
007 ta
008 170701s2017 ulkd bmAC 000c kor
040 ▼a 211009 ▼c 211009 ▼d 211009
085 0 ▼a 0510 ▼2 KDCP
090 ▼a 0510 ▼b 6D36 ▼c 1066
100 1 ▼a 이은상 ▼g 李殷相
245 1 0 ▼a 음성 인식을 위한 다중 심층 신경망 병렬 학습 = ▼x Parallel training for deep neural network based speech recognizers / ▼d 李殷相
260 ▼a 서울 : ▼b 고려대학교 대학원, ▼c 2017
300 ▼a vi, 52장 : ▼b 도표 ; ▼c 26 cm
500 ▼a 지도교수: 陸東錫
500 ▼a 부록: A. 최적의 epoch 설정
502 0 ▼a 학위논문(석사)-- ▼b 고려대학교 대학원, ▼c 컴퓨터·전파통신공학과, ▼d 2017. 8
504 ▼a 참고문헌: 장 49-52
530 ▼a PDF 파일로도 이용가능; ▼c Requires PDF file reader(application/pdf)
653 ▼a deep learning ▼a parallel training ▼a speech recognition ▼a deep neural network
776 0 ▼t parallel training for deep neural network based speech recognizers ▼w (DCOLL211009)000000076704
900 1 0 ▼a 육동석, ▼g 陸東錫, ▼d 1963-, ▼e 지도교수 ▼0 AUTH(211009)153275
945 ▼a KLPA

Electronic Information

No. Title Service
1
음성 인식을 위한 다중 심층 신경망 병렬 학습 (116회 열람)
View PDF Abstract Table of Contents

Holdings Information

No. Location Call Number Accession No. Availability Due Date Make a Reservation Service
No. 1 Location Science & Engineering Library/Stacks(Thesis)/ Call Number 0510 6D36 1066 Accession No. 123056959 Availability Available Due Date Make a Reservation Service B M

Contents information

Abstract

The hybrid deep neural Network (DNN) and hidden Markov model (HMM) have recently achieved great performance in speech recognition. However, the computing hardware was not adequate to learn deep neural networks with more hidden layers from big data sets. Further, despite the powerful performance of a DNN-based acoustic model, the time-consuming learning process has been a problem. This paper proposes a novel DNN-based acoustic modeling framework for speech recognition. The new model adopts parallel training in multiple DNNs. Several hierarchically structured DNNs are trained separately in parallel, using multiple computing units. Weights are averaged after each epoch. The suggested structure separates DNN into 10 and shows approximately 7.5 times faster in training time than baseline hybrid deep neural network. This improvement in average training time is mainly attributed to the use of multiple GPUs and the fact that training is based on only a subset of data in parallel. The WSJ data set was used for proposed parallel DNN performance verification.

Table of Contents

목 차
제 1 장 서론 1
제 2 장 관련 연구 4
2.1 Multi-layer perceptron(MLP) 4
2.2 Error backpropagation 9
2.3 Pre-training and fine-tuning 13
2.3.1 Deep Belief Network 14
제 3 장 DNN의 병렬 학습 방법 22
3.1 Model parallelism 23
3.2 Data parallelism 27
3.3 제안하는 parallel DNN 학습 방법 30
제 4 장 실험 및 결과 35
4.1 실험 환경 35
4.2 실험 결과 37
4.2.1 Baseline DNN-HMM 37
4.2.2 제안하는 방법 39
제 5 장 결론 및 향후 과제 44
부록 A. 최적의 epoch 설정 46
참고 문헌 49