Generating Synthetic Speech from SpokenVocab for Speech Translation.
Jinming ZhaoGholamreza HaffariEhsan ShareghiPublished in: CoRR (2022)
Keyphrases
- speech recognition
- speech signal
- speech synthesis
- hearing impaired
- endpoint detection
- speech processing
- text to speech
- automatic speech recognition
- speaker recognition
- language acquisition
- neural network
- recognition engine
- broadcast news
- spoken language
- dialogue system
- audio visual
- noisy environments
- machine translation
- multi stream
- human computer interaction
- face recognition
- real world
- database