Mel-Frequency Cepstral Coefficients Mubvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. Ko iyo 'mel' muMFCC inorevei?
   • Zita remuvambi
   • Rudzi rweneural network layer
   • Chiyero cheruzha mumadecibel
   • Chikero chefrequency chinoteedzera kunzwa kwemunhu
2. Ndeipi shanduko inoshandiswa kwekupedzisira kugadzira cepstral coefficients?
   • Discrete cosine shanduko
   • Fourier shanduko
   • Wavelet shanduko
   • Hilbert kuchinja
3. Sei maMFCC akasimba kusvika pakutaura kwemutauri?
   • Ivo vanowedzera iyo yakakosha frequency
   • Iyo DCT inoparadzanisa inononoka yezwi-turakiti chimiro kubva nekukurumidza pitch harmonics
   • Ivo vanofuratira amplitude zvachose
   • Vanoshandura odhiyo kuita zvinyorwa kutanga
4. Anenge mangani maMFCC coefficients anowanzo chengetwa pafuremu?
   • 100 chaiyo
   • Around 1,000
   • Around 13
   • 1 chete
5. Sei danda richishandiswa kune mel-band simba?
   • Kushandura kuita zvinyorwa
   • Kubvisa ruzha rwese zvakakwana
   • Kuwedzera sampling rate
   • Kufungidzira kuti vanhu vanoona sei ruzha
6. Mumaodhiyo emazuva ano akadzama ekudzidza, chii chinowanzotsiva maMFCC akagadzirwa nemaoko?
   • Raw waveforms kana log-mel spectrograms akadyiswa mune akadzidza kumberi-kumagumo
   • Manyorerwo asina kunyorwa
   • Iyo Fourier chete inoshandura isina kuyera
   • MIDI mafaira
7. What do the MFCCs summarize after the discrete cosine transform?
   • The original waveform sample by sample
   • A compact representation of the log mel-spectrum’s broad shape
   • The exact phase of every frequency component
   • The semantic meaning of a spoken sentence
8. What information is lost when a signal is summarized by a small set of MFCCs?
   • The recording’s entire duration
   • Every estimate of average loudness
   • Fine spectral detail and phase information
   • The existence of a time axis