The HW-TSC's Simultaneous Speech-to-Speech Translation System for IWSLT 2023 Evaluation.
Hengchao ShangZhiqiang RaoZongyao LiZhanglin WuJiaxin GuoMinghan WangDaimeng WeiShaojun LiZhengzhe YuXiaoyu ChenLizhi LeiHao YangPublished in: IWSLT@ACL (2023)
Keyphrases
- speech recognition
- speech signal
- speech synthesis
- audio visual
- text to speech
- spoken language
- broadcast news
- genetic algorithm
- data sets
- endpoint detection
- recognition engine
- vocal tract
- text to speech synthesis
- speech processing
- multi lingual
- speaker identification
- language acquisition
- dialogue system
- evaluation methods
- evaluation metrics
- evaluation method
- multi modal
- probabilistic model
- case study
- information systems