A Comparison of Hybrid and End-to-End ASR Systems for the IberSpeech-RTVE 2020 Speech-to-Text Transcription Challenge

A Comparison of Hybrid and End-to-End ASR Systems for the IberSpeech-RTVE 2020 Speech-to-Text Transcription Challenge

This paper describes a comparison between hybrid and end-to-end Automatic Speech Recognition (ASR) systems, which were evaluated on the IberSpeech-RTVE 2020 Speech-to-Text Transcription Challenge. Deep Neural Networks (DNNs) are becoming the most promising technology for ASR at present. In the last...

Full description

Bibliographic Details
Main Authors: Juan M. Perero-Codosero, Fernando M. Espinoza-Cuadros, Luis A. Hernández-Gómez
Format: Article
Language:English
Published: MDPI AG 2022-01-01
Series:Applied Sciences
Subjects:
TV show speech-to-text transcription
ASR systems
hybrid DNN-HMM
end-to-end deep learning
domain adversarial training
Online Access:https://www.mdpi.com/2076-3417/12/2/903

Internet

https://www.mdpi.com/2076-3417/12/2/903

Similar Items