Hyperparameter experiments on end-to-end automatic speech recognition
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 양형원 | - |
dc.contributor.author | 남호성 | - |
dc.date.accessioned | 2022-03-06T09:40:34Z | - |
dc.date.available | 2022-03-06T09:40:34Z | - |
dc.date.created | 2022-02-10 | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 2005-8063 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/137968 | - |
dc.description.abstract | End-to-end (E2E) automatic speech recognition (ASR) has achieved promising performance gains with the introduced self-attention network, Transformer. However, due to training time and the number of hyperparameters, finding the optimal hyperparameter set is computationally expensive. This paper investigates the impact of hyperparameters in the Transformer network to answer two questions: which hyperparameter plays a critical role in the task performance and training speed. The Transformer network for training has two encoder and decoder networks combined with Connectionist Temporal Classification (CTC). We have trained the model with Wall Street Journal (WSJ) SI-284 and tested on devl93 and eval92. Seventeen hyperparameters were selected from the ESPnet training configuration, and varying ranges of values were used for experiments. The result shows that “num blocks” and “linear units” hyperparameters in the encoder and decoder networks reduce Word Error Rate (WER) significantly. However, performance gain is more prominent when they are altered in the encoder network. Training duration also linearly increased as “num blocks” and “linear units” hyperparameters’ values grow. Based on the experimental results, we collected the optimal values from each hyperparameter and reduced the WER up to 2.9/1.9 from dev93 and eval93 respectively. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | 한국음성학회 | - |
dc.title | Hyperparameter experiments on end-to-end automatic speech recognition | - |
dc.title.alternative | Hyperparameter experiments on end-to-end automatic speech recognition | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | 남호성 | - |
dc.identifier.bibliographicCitation | 말소리와 음성과학, v.13, no.1, pp.45 - 51 | - |
dc.relation.isPartOf | 말소리와 음성과학 | - |
dc.citation.title | 말소리와 음성과학 | - |
dc.citation.volume | 13 | - |
dc.citation.number | 1 | - |
dc.citation.startPage | 45 | - |
dc.citation.endPage | 51 | - |
dc.type.rims | ART | - |
dc.identifier.kciid | ART002699005 | - |
dc.description.journalClass | 2 | - |
dc.description.journalRegisteredClass | kci | - |
dc.subject.keywordAuthor | automatic speech recognition | - |
dc.subject.keywordAuthor | hyperparameters | - |
dc.subject.keywordAuthor | neural network | - |
dc.subject.keywordAuthor | optimization | - |
dc.subject.keywordAuthor | transformer | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.