Simultaneous Speech-to-Speech Translation System with Transformer-Based Incremental ASR, MT, and TTS.
Ryo FukudaSashi NovitasariYui OkaYasumasa KanoYuki YanoYuka KoHirotaka TokuyamaKosuke DoiTomoya YanagitaSakriani SaktiKatsuhito SudohSatoshi NakamuraPublished in: O-COCOSDA (2021)
Keyphrases
- text to speech
- automatic speech recognition
- speech recognition
- speech signal
- speech synthesis
- machine translation
- spontaneous speech
- speech corpus
- noisy environments
- artificial intelligence
- endpoint detection
- conversational speech
- word error rate
- spoken words
- prosodic features
- vocal tract
- broadcast news
- spoken language
- recognition errors
- hidden markov models
- speaker identification
- human machine interaction
- speech recognizer
- linear prediction
- dialogue system
- query translation
- incremental version
- audio visual
- fuzzy logic
- pattern recognition
- information retrieval