Improving Speech-to-Speech Translation Through Unlabeled Text.
Xuan-Phi NguyenSravya PopuriChanghan WangYun TangIlia KulikovHongyu GongPublished in: ICASSP (2023)
Keyphrases
- text to speech
- speech recognition
- text to speech synthesis
- english text
- text recognition
- speech signal
- multi lingual
- spontaneous speech
- speech synthesis
- database
- text input
- spoken language
- text mining
- audio visual
- automatic speech recognition
- broadcast news
- machine translation
- semantic information
- vocal tract
- unlabeled data
- lexical features
- labeled data
- spoken documents
- supervised learning