Text spotting in large speech databases for under-resourced languages.
Andi BuzoHoria CucuCorneliu BurileanuPublished in: SpeD (2013)
Keyphrases
- databases
- english text
- multi lingual
- text to speech
- text to speech synthesis
- database
- spoken language
- document analysis
- text summarization
- text recognition
- relational databases
- language identification
- language independent
- speech recognition
- lexical features
- text input
- keyword spotting
- arabic language
- automatic speech recognition
- information retrieval
- cross lingual
- conversational speech
- speech synthesis
- natural language generation
- data sources
- spoken documents
- text retrieval
- text databases
- speech signal
- expressive power
- database languages
- spontaneous speech
- data model
- database systems
- text documents
- optical character recognition
- data management
- manually constructed
- language specific
- speech processing
- search engine
- metadata
- broadcast news