Audio-linguistic Embeddings for Spoken Sentences.
Albert HaqueMichelle GuoPrateek VermaLi Fei-FeiPublished in: ICASSP (2019)
Keyphrases
- natural language
- linguistic features
- syntactic structures
- broadcast news
- spoken documents
- linguistic analysis
- syntactic analysis
- semantic representations
- language understanding
- multimedia
- phrase structure
- natural language processing
- linguistic patterns
- text generation
- natural language understanding
- speech recognition
- vector space
- visual information
- linguistic expressions
- spoken language
- dimensionality reduction
- sentence level
- signal processing
- low dimensional
- audio stream
- multi document summarization
- linguistic information
- natural language text
- language processing
- euclidean space
- audio visual
- semantic analysis
- linguistic knowledge
- text summarization
- parse tree
- automatic summarization
- word order
- spoken document retrieval
- manifold learning
- high dimensional data
- audio files
- automatic speech recognition
- hilbert space
- information extraction
- spoken words