Predicting Severity of Voice Disorder from DNN-HMM Acoustic Posteriors.
Tan LeeYuanyuan LiuYu Ting YeungThomas K. T. LawKathy Y. S. LeePublished in: INTERSPEECH (2016)
Keyphrases
- hidden markov models
- speech sounds
- speech signal
- speech recognition
- mel frequency cepstral coefficients
- speaker independent
- acoustic signal
- automatic speech recognition
- handwritten word recognition
- acoustic features
- underwater acoustic
- multi stream
- training process
- gesture recognition
- feature vectors
- text to speech
- underwater vehicles
- pixel wise
- prosodic features
- voice and data services