Enhancement of electrolarynx speech based on perceptual weighting.
Ya BaiMingxi WanSupin WangPublished in: BMEI (2012)
Keyphrases
- speech recognition
- image enhancement
- image processing
- speech signal
- human visual system
- audio visual
- recognition engine
- speaker recognition
- automatic speech recognition
- low level
- spoken language
- speaker identification
- text to speech
- human perception
- speech synthesis
- endpoint detection
- vocal tract
- neural network
- language acquisition
- visual perception
- similarity measure
- dialogue system
- broadcast news
- speaker verification
- weighting scheme
- tf idf
- multi lingual
- hidden markov models
- speech recognizer
- computer vision
- data sets
- text to speech synthesis
- hearing impaired