ew 20(27): e4

Research Article

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

Download134 downloads
  • @ARTICLE{10.4108/eai.13-7-2018.164109,
        author={Manuel Quintana and Miguel Bernal},
        title={A Direct Speech-to-Speech Neural Network Methodology for Spanish-English Translation},
        journal={EAI Endorsed Transactions on Energy Web},
        volume={7},
        number={27},
        publisher={EAI},
        journal_a={EW},
        year={2020},
        month={4},
        keywords={Speech processing, Neural networks, Pattern Recognition},
        doi={10.4108/eai.13-7-2018.164109}
    }
    
  • Manuel Quintana
    Miguel Bernal
    Year: 2020
    A Direct Speech-to-Speech Neural Network Methodology for Spanish-English Translation
    EW
    EAI
    DOI: 10.4108/eai.13-7-2018.164109
Manuel Quintana1, Miguel Bernal1,*
  • 1: Dept. of Electrical and Electronics Engineering, Sonora Institute of Technology, 5 de Febrero 818 Sur, C.P. 85000, Cd. Obregon, Mexico
*Contact email: miguel.bernal@itson.edu.mx

Abstract

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.