Maswali yanayounganishwa na mwongozo · Ngumu Kiwango

Maswali ya Vipengele vya Filterbank na PLP

Jaribu jinsi benki za vichungi vya log-mel na PLP zinavyobadilisha fremu fupi za usemi kuwa vipengele vyenye umbo la kutamka kwa miundo ya kisasa ya usemi.

Njia za mwongozo zinazohusianaFilterbank Na Vipengele vya Plp
Swali 1 ya 8

Why do speech filterbanks use mel- or Bark-spaced bands instead of uniformly spaced hertz?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Why do speech filterbanks use mel- or Bark-spaced bands instead of uniformly spaced hertz?
    • The scales allocate finer frequency spacing at low frequencies and coarser spacing at high frequencies, approximating aspects of hearing
    • They make files smaller only
    • They remove all background noise
    • They guarantee perfect speech recognition
  2. Hatua ya utabiri wa mstari katika PLP inatimiza nini?
    • Inaongeza sauti
    • Inafaa bahasha laini ya spectral inayonasa umbo la njia ya sauti
    • Inaongeza kitenzi
    • Inabadilisha sauti kuwa maandishi moja kwa moja
  3. Ni aina gani ya vipengele ni ingizo kuu kwa miundo ya kisasa ya utambuzi wa usemi wa kina?
    • Faili ghafi za MIDI
    • Nakala zilizoandikwa kwa mkono
    • Vipengele vya benki ya kichujio cha logi
    • Vipimo vya JPEG
  4. Je, MFCCs hutofautiana vipi na huduma mbichi za kichujio cha log-mel?
    • MFCC hazitumii vichungi hata kidogo
    • MFCC hupimwa kwa desibeli pekee
    • MFCC zinahitaji safu ya maikrofoni
    • MFCC huongeza ubadilishaji wa cosine ili kupamba matokeo ya benki ya vichungi
  5. Je, ni kipengele gani cha utambuzi ambacho PLP inajumuisha ambacho benki za msingi za kichujio hazifanyi?
    • Mviringo wa sauti ya usawa na mgandamizo wa mchemraba-mzizi
    • Mfano wa lugha iliyojengwa
    • Tafsiri otomatiki
    • Uchimbaji wa stereo
  6. Why might a deep model use log-mel features or raw waveforms instead of PLP?
    • PLP ni kinyume cha sheria kutumia
    • The model can learn useful task-specific representations without every hand-designed PLP step
    • Sauti mbichi huwa ndogo kila wakati
    • PLP inafanya kazi kwa muziki pekee
  7. What is a typical log-mel filterbank feature for one speech frame?
    • A word-level translation
    • A single pitch label for the whole recording
    • The logarithm of spectral energy pooled through a mel-spaced filter
    • A pixel color from a spectrogram image
  8. Which order best describes the main PLP processing steps?
    • Translation, tokenization, and decoding
    • Stereo panning, reverb, and compression
    • Image segmentation followed by color correction
    • Critical-band analysis, equal-loudness weighting, loudness compression, then linear prediction