Acoustic normalization of children's speech.
Georg StemmerChristian HackerStefan SteidlElmar NöthPublished in: INTERSPEECH (2003)
Keyphrases
- hearing impaired
- speech recognition
- speech recognition systems
- speech sounds
- speech recognition technology
- acoustic features
- emotional speech
- speaker independent
- autistic children
- speech signal
- prosodic features
- automatic speech recognition
- acoustic models
- noisy speech
- emotion recognition
- acoustic signal
- formant frequencies
- text to speech
- speech synthesis
- source localization
- young children
- speech enhancement
- speech recognizers
- speaker verification
- speech recognizer
- vocal tract
- broadcast news
- audio visual
- school children
- speech segments
- vowel phonemes
- recognition engine
- normalization method
- linear prediction
- children learn
- audio stream
- educational software
- music information retrieval
- language acquisition
- noisy environments
- pilot study
- endpoint detection
- language model
- preprocessing
- pattern recognition