Fast-Slow Transformer for Visually Grounding Speech.
Puyuan PengDavid HarwathPublished in: CoRR (2021)
Keyphrases
- speech recognition
- fuzzy logic
- speech synthesis
- speech signal
- recognition engine
- fault diagnosis
- automatic speech recognition
- language acquisition
- speaker recognition
- expert systems
- hearing impaired
- power transformers
- multi lingual
- broadcast news
- spoken language
- audio visual
- power system
- control system
- evolutionary algorithm
- speech corpus
- endpoint detection
- search engine
- automatic speech recognition systems