NAIST Simultaneous Speech Translation System for IWSLT 2024
This work addresses simultaneous speech translation for multiple language pairs, presenting incremental improvements to existing methods for the IWSLT evaluation.
The paper describes NAIST's submission to the IWSLT 2024 simultaneous translation tasks, developing multilingual end-to-end speech-to-text models with Local Agreement decoding and an improved incremental speech-to-speech translation cascade, where the upgraded TTS module enhanced system performance.
This paper describes NAIST's submission to the simultaneous track of the IWSLT 2024 Evaluation Campaign: English-to-{German, Japanese, Chinese} speech-to-text translation and English-to-Japanese speech-to-speech translation. We develop a multilingual end-to-end speech-to-text translation model combining two pre-trained language models, HuBERT and mBART. We trained this model with two decoding policies, Local Agreement (LA) and AlignAtt. The submitted models employ the LA policy because it outperformed the AlignAtt policy in previous models. Our speech-to-speech translation method is a cascade of the above speech-to-text model and an incremental text-to-speech (TTS) module that incorporates a phoneme estimation model, a parallel acoustic model, and a parallel WaveGAN vocoder. We improved our incremental TTS by applying the Transformer architecture with the AlignAtt policy for the estimation model. The results show that our upgraded TTS module contributed to improving the system performance.