Age-dependent height estimation and speaker normalization for children's speech using the first three subglottal resonances.
Jinxi GuoRohit PaturiGary YeungSteven M. LulichHarish ArsikereAbeer AlwanPublished in: INTERSPEECH (2015)
Keyphrases
- speech recognition
- speech sounds
- automatic speech recognition
- speaker recognition
- audio visual
- speaker verification
- speaker identification
- hearing impaired
- speech signal
- vocal tract
- speech recognition technology
- speaker dependent
- speaker diarization
- speaker adaptation
- prosodic features
- speech synthesis
- parameter estimation
- autistic children
- young children
- acoustic features
- estimation algorithm
- school children
- pattern recognition
- noisy environments
- synthesized speech
- hidden markov models
- automatic speech recognition systems
- phoneme recognition
- older adults
- speaker independent
- spontaneous speech
- children learn
- age groups
- emotion recognition
- estimation accuracy
- vector quantization
- preprocessing