Investigating text normalization and pronunciation variants for German broadcast transcription.
Martine Adda-DeckerGilles AddaLori LamelPublished in: INTERSPEECH (2000)
Keyphrases
- spontaneous speech
- automatic transcription
- news video
- database
- information retrieval
- textual data
- text mining
- language learning
- text retrieval
- keywords
- speech recognition
- preprocessing
- normalization method
- text classification
- web documents
- semantic information
- text documents
- free text
- text summarization
- natural language generation
- speech recognition systems
- metadata