Improving Speech-to-Speech Translation Through Unlabeled Text.
Xuan-Phi NguyenSravya PopuriChanghan WangYun TangIlia KulikovHongyu GongPublished in: CoRR (2022)
Keyphrases
- text to speech
- text to speech synthesis
- speech recognition
- text recognition
- speech signal
- spontaneous speech
- multi lingual
- text input
- speech synthesis
- english text
- audio visual
- automatic speech recognition
- information retrieval
- spoken language
- text retrieval
- noisy environments
- conversational speech
- recognition engine
- lexical features
- spoken document retrieval
- dialogue system
- machine translation system
- vocal tract
- speaker identification
- broadcast news
- training data
- database
- language generation
- spoken documents
- affect sensing