The Kyoto Speech-to-Speech Translation System for IWSLT 2023
2023pp. 357–362
Citations Over Time
Abstract
This paper describes the Kyoto speech-to-speech translation system for IWSLT 2023. Our system is a combination of speech-to-text translation and text-to-speech synthesis. For the speech-to-text translation model, we used the dual-decoderTransformer model. For text-to-speech synthesis model, we took a cascade approach of an acoustic model and a vocoder.
Related Papers
- → An analysis of machine translation and speech synthesis in speech-to-speech translation system(2011)17 cited
- → Simultaneous Speech-to-Speech Translation System with Transformer-Based Incremental ASR, MT, and TTS(2021)1 cited
- → Simultaneous Speech-to-Speech Translation System with Neural Incremental ASR, MT, and TTS(2020)9 cited
- → Real-time text processing for Italian speech synthesis(2005)5 cited
- → Speaker recognition application in automatic speech-to-speech translation(2014)