욤미의 개발일지

[논문 리뷰] A Spelling Correction Model for End-to-End Speech Recognition 본문

Paper Review

[논문 리뷰] A Spelling Correction Model for End-to-End Speech Recognition

욤미 2021. 9. 9. 17:41
728x90
반응형

 

 

A spelling correction model for end-to-end speech recognition

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language model component of

arxiv.org

 

 

 

ㅁ

728x90
반응형
저작자표시 비영리 변경금지 (새창열림)

'Paper Review' 카테고리의 다른 글

[논문 리뷰] CodeBERT: A Pre-Trained Model for Programming and Natural Languages  (0) 2023.06.03
[논문 리뷰] Competition-Level Code Generation with AlphaCode  (0) 2023.05.05
[논문 리뷰] Multi-Classification Prediction of Alzheimer’sDisease based on Fusing Multi-modal Features  (0) 2023.04.05
[논문 리뷰] Resolution Dependent GAN Interpolation forControllable Image Synthesis Between Domains  (0) 2022.11.01
Federated Learning and Analytics: Industry Meets Academia  (0) 2021.08.17
'Paper Review' Related Articles more
Comments