Neural Vocoder

AbstractSpeech emotion conversion is the task of modifying the perceived emotion of a speech utterance while preserving the lexical content and speaker identity. In this study, we cast the problem …...

AbstractThis paper describes NAIST’s submission to the IWSLT 2023 Simultaneous Speech Translation task: English-to-German, Japanese, Chinese speech-to-text translation and English-to-Japanese speech-to-speech translation. Our speech-to-text system uses an end-to-end multilingual speech …...