A Direct Speech-to-Speech Neural Network Methodology for Spanish-English Translation

Quintana, Manuel and Bernal, Miguel (2020) A Direct Speech-to-Speech Neural Network Methodology for Spanish-English Translation. EAI Endorsed Transactions on Energy Web, 7 (27): 4. ISSN 2032-944X

[thumbnail of eai.13-7-2018.164109.pdf]
eai.13-7-2018.164109.pdf - Published Version
Available under License Creative Commons Attribution No Derivatives.

Download (2MB) | Preview


In this work, a novel direct speech-to-speech methodology for translation is proposed; it is based on an LSTM neural network structure which has proven useful for translation in the classical way, i.e., the one consisting of three stages: speech-to-text conversion, text-to-text translation, and text-to-speech synthesis. In contrast with traditional approaches, the one in this work belongs to the recently appeared idea of direct translation without text representation, as this sort of training better corresponds to the way oral language learning takes place in humans. As a proof of concept digits are translated from an audio source in Spanish and pronounced as an audio signal in English. Advantages and disadvantages of the proposal when compared with traditional methodologies are discussed.

Item Type: Article
Uncontrolled Keywords: Speech processing, Neural networks, Pattern Recognition
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
QA75 Electronic computers. Computer science
Depositing User: EAI Editor II.
Date Deposited: 17 Sep 2020 10:44
Last Modified: 17 Sep 2020 10:44
URI: https://eprints.eudl.eu/id/eprint/429

Actions (login required)

View Item
View Item