Modification of Velvet Noise for Speech Waveform Generation by Using Vocoder-Based Speech Synthesizer.
Masanori MorisePublished in: IEICE Trans. Inf. Syst. (2019)
Keyphrases
- text to speech
- speech recognition
- speech signal
- noisy environments
- speech synthesis
- speech enhancement
- audio visual
- automatic speech recognition
- fundamental frequency
- multimodal interfaces
- speaker recognition
- spoken language
- language acquisition
- recognition engine
- speaker verification
- noisy data
- information retrieval
- broadcast news
- background noise
- data sets
- emotion recognition
- noise level
- multi stream
- noise reduction
- multiscale