Weakly-Supervised Speech-to-Text Mapping with Visually Connected Non-Parallel Speech-Text Data Using Cyclic Partially-Aligned Transformer.
Johanes EffendiSakriani SaktiSatoshi NakamuraPublished in: Interspeech (2021)
Keyphrases
- text data
- weakly supervised
- text mining
- topic models
- text classification
- text documents
- high dimensional
- named entities
- superpixels
- structured data
- object class
- relation extraction
- document collections
- high dimensional data
- semi supervised
- information extraction
- machine learning
- artificial intelligence
- text categorization
- generative model
- object detection
- image retrieval
- object detectors
- object recognition
- web pages