Speak While You Think: Streaming Speech Synthesis During Text Generation.
Avihu DekelSlava ShechtmanRaul FernandezDavid HawsZvi KonsRon HooryPublished in: CoRR (2023)
Keyphrases
- speech synthesis
- text generation
- speech recognition
- natural language generation
- text to speech
- vocal tract
- natural language
- prosodic features
- real time streaming
- data streams
- automatic speech recognition
- theorem prover
- streaming data
- non stationary
- stream processing
- speech corpus
- real time
- scalable video
- machine learning
- domain knowledge
- expert systems
- multi agent systems
- image processing
- information retrieval
- streaming video
- streaming media
- data sets