Perceived Naturalness of Electrolaryngeal Speech Produced Using sEMG-Controlled vs. Manual Pitch Modulation.
Kathleen F. NagleJames T. HeatonPublished in: INTERSPEECH (2016)
Keyphrases
- speech recognition
- formant frequencies
- fundamental frequency
- speech signal
- acoustic features
- automatic transcription
- semi automatic
- error prone
- automatic speech recognition
- audio visual
- labor intensive
- speech transcripts
- information retrieval
- speech synthesis
- text to speech
- speaker recognition
- spoken language
- perceived usefulness
- neural network
- music information retrieval
- recognition engine
- noisy environments
- modulation scheme
- non stationary