Audiobox: Unified Audio Generation with Natural Language Prompts.
Apoorv VyasBowen ShiMatthew LeAndros TjandraYi-Chiao WuBaishan GuoJiemin ZhangXinyue ZhangRobert AdkinsWilliam NganJeff WangIvan CruzBapi AkulaAkinniyi AkinyemiBrian EllisRashel MoritzYael YungsterAlice RakotoarisonLiang TanChris SummersCarleigh WoodJoshua LaneMary WilliamsonWei-Ning HsuPublished in: CoRR (2023)
Keyphrases
- natural language
- text generation
- natural language interface
- machine learning
- signal processing
- natural language generation
- generation process
- human language
- visual data
- multimedia
- information extraction
- natural language processing
- question answering
- audio visual
- visual information
- semantic interpretation
- natural language understanding
- language processing
- data sets
- statistically significant
- low level
- neural network