Combining acoustic name spotting and continuous context models to improve spoken person name recognition in speech.
Benjamin BigotGrégory SenayGeorges LinarèsCorinne FredouilleRichard DufourPublished in: INTERSPEECH (2013)
Keyphrases
- speech recognition
- speech sounds
- spoken words
- speech recognition systems
- acoustic models
- keyword spotting
- automatic speech recognition
- recognition rate
- speaker independent
- recognition engine
- spoken language
- broadcast news
- document analysis
- feature extraction
- activity recognition
- object recognition
- object models
- speech signal
- contextual information
- pattern recognition