Frequency Domain Variants of Velvet Noise and Their Application to Speech Processing and Synthesis.
Hideki KawaharaKen-Ichi SakakibaraMasanori MoriseHideki BannoTomoki TodaToshio IrinoPublished in: INTERSPEECH (2018)
Keyphrases
- frequency domain
- speech processing
- power spectrum
- spatial domain
- fourier transform
- power spectra
- feature extraction
- denoising
- speech recognition
- cross correlation
- speaker identification
- signal processing
- noisy environments
- machine learning
- subband
- signal to noise ratio
- database systems
- speech signal
- image processing
- fast fourier transform
- computer vision