NAIST Simultaneous Speech-to-speech Translation System for IWSLT 2023.
Ryo FukudaYuta NishikawaYasumasa KanoYuka KoTomoya YanagitaKosuke DoiMana MakinaeSakriani SaktiKatsuhito SudohSatoshi NakamuraPublished in: IWSLT@ACL (2023)
Keyphrases
- speech recognition
- speech signal
- automatic speech recognition
- recognition engine
- neural network
- endpoint detection
- multi modal
- machine translation
- speaker recognition
- vocal tract
- text to speech synthesis
- data sets
- audio stream
- finite state transducers
- speech synthesis
- text to speech
- broadcast news
- noisy environments
- multimedia
- learning algorithm