Flexible Keyword Spotting Based on Homogeneous Audio-Text Embedding.
Kumari NishuMinsik ChoPaul DixonDevang NaikPublished in: ICASSP (2024)
Keyphrases
- keyword spotting
- printed documents
- handwritten documents
- speech processing
- document images
- multimedia
- hidden markov models
- speech recognition
- character recognition
- text retrieval
- information retrieval
- text documents
- document analysis
- keywords
- web documents
- signal processing
- vector space
- audio visual
- image processing
- artificial intelligence
- text mining
- information extraction
- language independent
- textual data
- text processing
- digital libraries
- natural language generation
- text to speech
- computer vision