AlloST: Low-Resource Speech Translation Without Source Transcription.
Yao-Fei ChengHung-Shin LeeHsin-Min WangPublished in: Interspeech (2021)
Keyphrases
- speech recognition
- automatic transcription
- speech recognition technology
- resource allocation
- speech recognition systems
- target language
- machine translation
- high levels
- spontaneous speech
- text to speech
- spoken language
- speaker verification
- handwriting recognition
- automatic speech recognition
- query translation
- noisy environments
- multimodal interfaces
- out of vocabulary
- speech synthesis
- speech signal
- audio visual
- neural network