(주) 뷰노

(주) 뷰노

문의사항 남기기
KR EN
Publications
BACK TO LIST
Interspeech 2020

Evolved Speech-Transformer: Applying Neural Architecture Search to End-to-End Automatic Speech Recognition

  • Oct. 2020
  • by Jihwan Kim et. al.

Neural architecture search (NAS) has been successfully applied to finding efficient, high-performance deep neural network architectures in a task-adaptive manner without extensive human intervention. This is achieved by choosing genetic, reinforcement learning, or gradient -based algorithms as automative alternatives of manual architecture design. However, a naive application of existing NAS algorithms to different tasks may result in architectures which perform sub-par to those manually designed. In this work, we show that NAS can provide efficient architectures that outperform manually designed attention-based architectures on speech recognition tasks, after which we named Evolved Speech-Transformer (EST). With a combination of carefully designed search space and Progressive dynamic hurdles, a genetic algorithm based, our algorithm finds a memory-efficient architecture which outperforms vanilla Transformer with reduced training time.

Link

https://www.isca-speech.org/archive/Interspeech_2020/abstracts/1233.html

Author

Jihwan Kim, Jisung Wang, Sangki Kim, and Yeha Lee

Tag in

#medical_records

#VUNO Med®-Deep ASR™

#speech_recognition

이전글
Graph Convolutional Networks-based Noisy Data Imputation in Electronic Health Record 2020. 11. 30
다음글
Exploring Lexicon-Free Modeling Units for End-to-End Korean and Korean-English Code-Switching Speech Recognition 2020. 11. 30
List

이 웹사이트는 원활한 서비스 제공을 위하여 당사 개인정보 처리방침에 명시된 쿠키를 사용합니다.

만일 당사의 쿠키 사용 정책에 대해 더 알고 싶으신 경우에는 개인정보 처리방침 을 참고하여 주시기 바랍니다.