Combination of Time-domain, Frequency-domain, and Cepstral-domain Acoustic Features for Speech Commands Classification.
Yikang WangHiromitsu NishizakiPublished in: CoRR (2022)
Keyphrases
- frequency domain
- cross correlation
- acoustic features
- feature extraction
- spatial domain
- mel frequency cepstral coefficients
- audio features
- speech recognition
- classification accuracy
- denoising
- speech signal
- spectral domain
- speaker verification
- subband
- pattern recognition
- feature selection
- automatic speech recognition
- feature vectors
- high level
- power spectra
- visual features
- music information retrieval
- image classification
- speaker recognition
- multiscale
- computer vision
- frequency domain analysis