Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 장준혁 | - |
dc.date.accessioned | 2022-11-02T04:55:06Z | - |
dc.date.available | 2022-11-02T04:55:06Z | - |
dc.date.issued | 2021-02 | - |
dc.identifier.citation | TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, v. 29, no. 5, page. 2362-2373 | en_US |
dc.identifier.issn | 1300-0632; 1303-6203 | en_US |
dc.identifier.uri | https://journals.tubitak.gov.tr/elektrik/vol29/iss5/7/ | en_US |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/176209 | - |
dc.description.abstract | This study develops the deep Q-network (DQN)-based noise suppression for robust speech recognition purposes under ambient noise. We thus design a reinforcement algorithm that combines DQN training with a deep neural networks (DNN) to let reinforcement learning (RL) work for complex and high dimensional environments like speech recognition. For this, we elaborate on the DQN training to choose the best action that is the quantized noise suppression gain by the observation of noisy speech signal with the rewards of DQN including both the word error rate (WER) and objective speech quality measure. Experiments demonstrate that the proposed algorithm improves speech recognition in various noisy conditions while reducing the computational burden compared to the DNN-based noise suppression method. | en_US |
dc.description.sponsorship | This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2021-0-00456, Development of Ultra-high Speech Quality Technology for Remote Multi-speaker Conference System) . Joon-Hyuk CHANG gave the idea, Tae-JunPARK did the experiments, Tae-Jun PARK and Joon-Hyuk CHANG interpreted the results, Tae-Jun PARK wrote the paper. | en_US |
dc.language | en | en_US |
dc.publisher | TUBITAK SCIENTIFIC & TECHNICAL RESEARCH COUNCIL TURKEY | en_US |
dc.subject | Deep Q-network; reinforcement learning; speech recognition; noise suppression; speech enhancement; deep neural network | en_US |
dc.title | Deep Q-network-based noise suppression for robust speech recognition | en_US |
dc.type | Article | en_US |
dc.relation.no | 5 | - |
dc.relation.volume | 29 | - |
dc.identifier.doi | 10.3906/elk-2011-144 | en_US |
dc.relation.page | 2362-2373 | - |
dc.relation.journal | TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES | - |
dc.contributor.googleauthor | Park, Tae-Jun | - |
dc.contributor.googleauthor | Chang, Joon-Hyuk | - |
dc.relation.code | 2021002548 | - |
dc.sector.campus | S | - |
dc.sector.daehak | COLLEGE OF ENGINEERING[S] | - |
dc.sector.department | SCHOOL OF ELECTRONIC ENGINEERING | - |
dc.identifier.pid | jchang | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.