Enhancement of Electrolarynx speech based on WaveRNN.
Eturo UrabeRin HirakawaHideki KawanoKenichi NakashiYoshihisa NakatohPublished in: ACIT (2019)
Keyphrases
- speech recognition
- image enhancement
- text to speech
- recognition engine
- speech signal
- endpoint detection
- emotion recognition
- image processing
- automatic speech recognition
- audio visual
- spoken language
- dialogue system
- vocal tract
- computer vision
- hearing impaired
- audio stream
- speech synthesis
- data sets
- broadcast news
- linear prediction
- language acquisition
- image analysis
- feature selection
- artificial intelligence
- machine learning