The HW-TSC's Speech-to-Speech Translation System for IWSLT 2023.
Minghan WangYinglu LiJiaxin GuoZongyao LiHengchao ShangDaimeng WeiMin ZhangShimin TaoHao YangPublished in: IWSLT@ACL (2023)
Keyphrases
- speech recognition
- audio visual
- automatic speech recognition
- speech synthesis
- endpoint detection
- recognition engine
- text to speech
- speech signal
- noisy environments
- vocal tract
- spoken language
- language acquisition
- pattern recognition
- neural network
- dialogue system
- broadcast news
- spoken dialogue systems
- image sequences
- multi lingual
- website
- multimedia
- learning algorithm
- audio stream
- information retrieval