Using Approximate Entropy as a speech quality measure for a speaker recognition system.
Richard A. MetzgerJohn F. DohertyDavid M. JenkinsPublished in: CISS (2016)
Keyphrases
- quality measures
- automatic speech recognition systems
- speech recognition
- speaker independent
- isolated word
- speaker recognition
- recognition engine
- speech signal
- audio visual
- automatic speech recognition
- speaker identification
- speaker verification
- speaker dependent
- hidden markov models
- speaker diarization
- speech synthesis
- noisy speech
- prosodic features
- speech recognizer
- speaker adaptation
- vocal tract
- feature extraction
- acoustic models
- gaussian mixture model
- language model
- noisy environments
- emotion recognition
- spoken language
- audio stream
- acoustic features
- speech sounds
- synthesized speech
- broadcast news